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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "no idea" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a lack of knowledge or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inka
    -0.84
    vertisement
    -0.70
    cedes
    -0.70
    andise
    -0.69
    visor
    -0.69
    die
    -0.67
    conservancy
    -0.67
    iki
    -0.66
    anski
    -0.65
    pu
    -0.62
    POSITIVE LOGITS
     whatsoever
    0.99
     squat
    0.78
     how
    0.73
    ariat
    0.71
    UTH
    0.70
    rieve
    0.70
    RECT
    0.68
     guessing
    0.68
    icity
    0.67
     whence
    0.67
    Act Density 0.022%

    No Known Activations