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

    Neuronpedia

    INDEX
    Explanations

    words related to impactful events or occurrences that shake a system or community

    oai_token-act-pair · gpt-3.5-turbo

    events or situations that cause significant disruption or upheaval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.79
    ittees
    -0.77
    orescent
    -0.70
    uses
    -0.70
    idates
    -0.67
    ript
    -0.65
    uded
    -0.65
    ately
    -0.64
    odore
    -0.63
    endi
    -0.63
    POSITIVE LOGITS
     rocked
    1.04
     rocking
    0.98
    stead
    0.87
    rock
    0.79
     Funk
    0.75
    castle
    0.71
     rock
    0.70
    neck
    0.69
    tones
    0.69
    crow
    0.69
    Act Density 0.005%

    No Known Activations