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

    Neuronpedia

    INDEX
    Explanations

    expressions of capability and ethics regarding actions

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

    "[pronoun] can" construction

    np_acts-logits-general · gemini-2.0-flash

    doing what one can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.97
    parsedMessage
    -0.73
    ">—
    -0.66
     quoque
    -0.62
     ainfi
    -0.62
     continúas
    -0.60
     truer
    -0.60
    twimg
    -0.60
    AddHtmlAttribute
    -0.59
    دانشنامهٔ
    -0.59
    POSITIVE LOGITS
     possibly
    1.16
    possibly
    1.03
     Possibly
    0.97
     possible
    0.95
    Possibly
    0.86
    possible
    0.82
     POSS
    0.79
     Possible
    0.78
    reasonably
    0.72
     human
    0.71
    Act Density 0.126%

    No Known Activations