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

    Neuronpedia

    INDEX
    Explanations

    sequences related to meetings or interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of informal language or colloquial expressions related to social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.75
     Nare
    -0.70
     Corpus
    -0.70
    edIn
    -0.67
     millenn
    -0.65
     affected
    -0.63
     Vie
    -0.59
    swick
    -0.59
     referen
    -0.59
    ħĭ
    -0.58
    POSITIVE LOGITS
    trade
    0.97
    advertising
    0.96
    gallery
    0.92
    everything
    0.90
    hold
    0.89
    shoot
    0.89
    return
    0.89
    your
    0.88
    exec
    0.88
    comments
    0.86
    Act Density 0.025%

    No Known Activations