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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.82
    AccessorTable
    -0.75
    ſelf
    -0.73
     themſelves
    -0.70
     myſelf
    -0.69
     itſelf
    -0.69
    ^(@)
    -0.67
    AnchorStyles
    -0.67
     bershka
    -0.64
     oprot
    -0.64
    POSITIVE LOGITS
     y
    0.48
    FormUrlEncoded
    0.46
     or
    0.46
     avena
    0.46
     x
    0.43
     Poole
    0.43
    urlencoded
    0.43
     X
    0.43
    TacToe
    0.42
    saraba
    0.41
    Act Density 1.087%

    No Known Activations