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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.86
     فريبيس
    -0.76
    MessageOf
    -0.63
     otomatig
    -0.62
    permitAll
    -0.62
    PreferredItem
    -0.61
     @"/
    -0.59
    podar
    -0.59
    стоян
    -0.58
    IsPostBack
    -0.58
    POSITIVE LOGITS
     unlike
    0.96
     importantly
    0.86
     contrary
    0.84
    unlike
    0.81
     parado
    0.78
     unfortunately
    0.75
     conversely
    0.74
     ironically
    0.73
     interestingly
    0.73
     besides
    0.70
    Act Density 0.143%

    No Known Activations