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

    Neuronpedia

    INDEX
    Explanations

    instances where the term "talks" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to discussions or negotiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olls
    -0.77
    ribution
    -0.66
    ographic
    -0.64
    ross
    -0.64
    Lake
    -0.61
    lesi
    -0.61
    inion
    -0.60
    ously
    -0.60
    Notable
    -0.59
    ographically
    -0.59
    POSITIVE LOGITS
    pace
    0.93
    paces
    0.83
     negotiations
    0.81
     warr
    0.81
    poons
    0.80
    hops
    0.79
     underway
    0.78
    afety
    0.77
    pire
    0.73
    hooting
    0.73
    Act Density 0.045%

    No Known Activations