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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is being contacted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contacted"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bur
    -0.76
    puff
    -0.75
    few
    -0.74
    serving
    -0.71
    scar
    -0.69
    imposed
    -0.69
    acre
    -0.68
    eat
    -0.65
     emphasis
    -0.65
    stroke
    -0.64
    POSITIVE LOGITS
     him
    0.79
    ADRA
    0.73
     superiors
    0.71
     us
    0.70
     advertisers
    0.68
     Ars
    0.67
     them
    0.66
     SOS
    0.65
     Aires
    0.64
     acquaintances
    0.64
    Act Density 0.072%

    No Known Activations