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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.58
    gridx
    -0.56
    BackStack
    -0.55
     Finlay
    -0.54
    PostExecute
    -0.53
    وا
    -0.52
    ↵
    -0.52
     Dwayne
    -0.52
    writeHead
    -0.51
    keras
    -0.51
    POSITIVE LOGITS
    IZABETH
    0.78
     Maryam
    0.76
     ANN
    0.75
    ItemBackground
    0.75
    ydd
    0.74
    vonne
    0.73
     Мексичка
    0.73
    maries
    0.73
     Elbe
    0.72
     Ann
    0.72
    Act Density 0.346%

    No Known Activations