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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or directives typically associated with recommendations or guidance

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

    Followed by an infinitive verb

    np_acts-logits-general · gemini-2.0-flash

    to followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    -0.49
    τία
    -0.47
     VIAF
    -0.45
    готовка
    -0.44
    forderung
    -0.44
    mont
    -0.44
    份
    -0.43
    penny
    -0.43
     arte
    -0.42
     реб
    -0.41
    POSITIVE LOGITS
    Vidite
    0.82
     للمعارف
    0.80
     help
    0.78
    twimg
    0.75
    JspWriter
    0.73
    TypedDataSet
    0.71
    addCriterion
    0.70
     autorytatywna
    0.69
     BrowserModule
    0.67
     FontWeight
    0.67
    Act Density 0.186%

    No Known Activations