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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate changes in emotional states or significant actions affecting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.66
    /
    -0.44
     be
    -0.44
    .
    -0.43
     .
    -0.42
    ,
    -0.42
    <eos>
    -0.42
    Pass
    -0.41
    ↵↵
    -0.39
     bar
    -0.39
    POSITIVE LOGITS
    TagMode
    1.01
    تقاوى
    0.99
     disambiguazione
    0.97
     defaultstate
    0.95
    ImageContext
    0.93
    tagext
    0.93
    AndEndTag
    0.92
    TypedDataSet
    0.92
     itſelf
    0.91
     Référence
    0.87
    Act Density 0.670%

    No Known Activations