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

    Neuronpedia

    INDEX
    Explanations

    question words or phrases related to uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions expressing uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igenous
    -0.69
    ciating
    -0.66
    rection
    -0.64
    cible
    -0.63
    naissance
    -0.63
    acco
    -0.62
    aten
    -0.62
    iferation
    -0.62
    byter
    -0.61
    processing
    -0.59
    POSITIVE LOGITS
     how
    0.92
     what
    0.89
    what
    0.88
    ?!
    0.84
    !?
    0.83
     if
    0.83
    ???
    0.83
     why
    0.82
    ?
    0.82
     whether
    0.82
    Act Density 0.043%

    No Known Activations