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

    Neuronpedia

    INDEX
    Explanations

    instances of situations involving the absence or lack of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aly
    -0.74
    ean
    -0.72
    lish
    -0.67
    Bloomberg
    -0.66
    mire
    -0.66
    inarily
    -0.63
     WATCHED
    -0.62
    late
    -0.62
    ammad
    -0.62
    amon
    -0.62
    POSITIVE LOGITS
    xious
    1.23
     discern
    1.11
     clue
    1.03
     detectable
    1.02
     indication
    0.97
     meaningful
    0.95
     shortage
    0.95
    oses
    0.93
     obvious
    0.92
     measurable
    0.91
    Act Density 0.101%

    No Known Activations