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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dashes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewChild
    -0.76
     kaynağından
    -0.72
    .
    -0.70
    ?
    -0.69
    "):
    -0.69
    matchCondition
    -0.68
    -0.64
    󠁢
    -0.61
    MigrationBuilder
    -0.61
    numerusform
    -0.60
    POSITIVE LOGITS
     myſelf
    0.89
     démocr
    0.83
     itſelf
    0.81
     themſelves
    0.81
     ſy
    0.81
     purpoſe
    0.80
     occaf
    0.78
     ainfi
    0.77
     pleaf
    0.77
     eenige
    0.77
    Act Density 0.577%
    No Known Activations