© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3045
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Memor
    -0.61
     learnt
    -0.60
     Gladiator
    -0.60
    roach
    -0.58
    itness
    -0.58
     convol
    -0.56
     arrog
    -0.56
     realizes
    -0.55
     remembers
    -0.54
     DSL
    -0.54
    POSITIVE LOGITS
    prison
    0.70
    leep
    0.70
    VERSION
    0.69
    ues
    0.66
    inate
    0.66
    allowed
    0.63
     occur
    0.61
    bourne
    0.60
    PT
    0.60
    �
    0.60
    Activations Density 0.025%

    No Known Activations