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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or possibility

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

    "possibly" and similar words

    np_acts-logits-general · gemini-2.0-flash

    introduces possible explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.69
    principalTable
    -0.67
     betweenstory
    -0.65
     nahilalakip
    -0.62
    OGND
    -0.60
    WaitGroup
    -0.59
    tagHelperRunner
    -0.59
    amaño
    -0.56
    awtextra
    -0.55
    󠁢
    -0.55
    POSITIVE LOGITS
     possibly
    0.96
     perhaps
    0.91
    possibly
    0.86
     Possibly
    0.85
    perhaps
    0.81
    Possibly
    0.81
     Perhaps
    0.77
     maybe
    0.75
     quizás
    0.74
    Perhaps
    0.73
    Act Density 0.619%

    No Known Activations