Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of programming and software development terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hs
    -0.20
    ss
    -0.18
    461
    -0.16
    ci
    -0.16
    cs
    -0.16
    ews
    -0.15
    233
    -0.15
    son
    -0.15
    665
    -0.15
    ogg
    -0.15
    POSITIVE LOGITS
    acemark
    0.15
    PTS
    0.15
    ellar
    0.14
     Shapiro
    0.14
    PUR
    0.14
    cales
    0.14
    dol
    0.14
    orca
    0.14
    itet
    0.13
    lotte
    0.13
    Act Density 0.644%

    No Known Activations