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

    Neuronpedia

    INDEX
    Explanations

    dialogue and interactions between characters

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

    Punctuation before spoken dialogue

    np_acts-logits-general · gemini-2.0-flash

    dialogue pauses or continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.82
    bootstrapcdn
    -0.76
     CreateTagHelper
    -0.72
    исленность
    -0.69
     faſt
    -0.68
    NameInMap
    -0.67
    }{*}{}
    -0.65
    IonicModule
    -0.64
     ―――――
    -0.64
     Anſ
    -0.63
    POSITIVE LOGITS
    说着
    0.81
    说完
    0.80
     tone
    0.55
     gest
    0.54
     tears
    0.54
    pause
    0.53
     *
    0.52
    话音
    0.52
     referring
    0.51
    *
    0.49
    Act Density 0.063%

    No Known Activations