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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'what' and questions or expressions of uncertainty

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

    what followed by verb or auxiliary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    colhead
    -0.41
    AnimationsModule
    -0.40
    SourceChecksum
    -0.38
    pAd
    -0.35
     ym
    -0.34
    ngdoc
    -0.34
     pinulongan
    -0.34
    UnusedPrivate
    -0.34
    ApiOperation
    -0.31
    GoogleApiClient
    -0.31
    POSITIVE LOGITS
     dieſer
    0.53
    󠁴
    0.52
     laſſen
    0.50
    culable
    0.50
    stoke
    0.50
    Wherever
    0.49
     Wherever
    0.49
    crank
    0.48
    lection
    0.48
    Activ
    0.47
    Act Density 0.015%

    No Known Activations