© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2445
    Prev
    Next
    INDEX
    Explanations

    the phrase "one of" used in various contexts

    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
    Beast
    -0.81
    soType
    -0.79
    CHAT
    -0.78
    Corp
    -0.76
    luaj
    -0.76
    ihara
    -0.72
    uner
    -0.72
    MpServer
    -0.72
    INAL
    -0.72
    Sense
    -0.71
    POSITIVE LOGITS
     summ
    0.73
     tears
    0.72
     withd
    0.70
     guts
    0.69
     heck
    0.67
     courage
    0.66
     sided
    0.65
     orchestr
    0.64
     brow
    0.64
     tele
    0.63
    Activations Density 0.033%

    No Known Activations