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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating impending danger or urgency

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases and constructs related to existential concepts and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omorphic
    -0.86
    ģĸ
    -0.69
    1001
    -0.63
    onite
    -0.61
    odic
    -0.61
    brid
    -0.60
    Pub
    -0.59
    _>
    -0.59
    bda
    -0.59
    ovember
    -0.59
    POSITIVE LOGITS
     they
    1.16
     he
    1.15
     she
    1.11
     we
    1.03
    she
    1.03
    they
    0.95
     you
    0.94
     He
    0.85
     SHE
    0.84
     I
    0.84
    Act Density 0.270%

    No Known Activations