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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rave
    -0.71
    wagon
    -0.69
     seriousness
    -0.60
    ADVERTISEMENT
    -0.60
    tsy
    -0.59
     trillion
    -0.57
     Growth
    -0.56
    Station
    -0.55
    orde
    -0.54
    take
    -0.54
    POSITIVE LOGITS
    ynchron
    0.74
    é¾įåĸļ士
    0.70
    azo
    0.67
    orah
    0.65
    undo
    0.65
    ado
    0.63
    velt
    0.62
    erson
    0.62
     dynamically
    0.62
    ociated
    0.61
    Act Density 0.058%

    No Known Activations