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

    Neuronpedia

    INDEX
    Explanations

    a collection of helping verbs and adverbs that often precede a verb.

    oai_token-act-pair · gemini-2.0-flash

    words related to programming functions or methods

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    keep
    -0.75
    Keep
    -0.73
     keep
    -0.73
     Keep
    -0.72
    Stay
    -0.70
     stay
    -0.69
     keeps
    -0.69
     Stay
    -0.69
    keeping
    -0.68
    stay
    -0.65
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.64
     HasFactory
    0.63
    таратура
    0.59
    IntoConstraints
    0.59
    WithIOException
    0.58
    ObjectModel
    0.57
     "..\..\
    0.57
    těte
    0.56
    jsoup
    0.55
     getStart
    0.54
    Act Density 6.880%

    No Known Activations