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

    Neuronpedia

    INDEX
    Explanations

    references to characters and their actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    textTheme
    -0.30
    的时间
    -0.27
    Referencies
    -0.26
     atractivos
    -0.26
    سطس
    -0.25
     OGSÅ
    -0.25
     vœ
    -0.25
    ställ
    -0.25
    ところ
    -0.25
    horabuena
    -0.25
    POSITIVE LOGITS
     betweenstory
    0.73
     nahilalakip
    0.67
    setVerticalGroup
    0.63
    StructEnd
    0.61
    DockStyle
    0.60
     Meksiku
    0.59
     الحره
    0.59
     invokingState
    0.55
    исленность
    0.52
     doInBackground
    0.52
    Act Density 0.033%

    No Known Activations