© 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. 3199
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to perception or belief

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    uyomi
    -0.75
     Negative
    -0.71
     Panic
    -0.69
     foregoing
    -0.67
     psychiat
    -0.66
    VALUE
    -0.63
    MAP
    -0.62
    uming
    -0.61
     srfAttach
    -0.60
     Darling
    -0.59
    POSITIVE LOGITS
    antes
    0.71
    \'
    0.71
    acles
    0.70
    acia
    0.69
    des
    0.69
    has
    0.69
     knew
    0.66
    aque
    0.66
     saw
    0.66
    acle
    0.64
    Activations Density 0.062%

    No Known Activations