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

    Neuronpedia

    INDEX
    Explanations

    statistics and numbers related to specific events or situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hub
    -0.61
    velength
    -0.61
     whipping
    -0.61
    sum
    -0.59
    amaru
    -0.58
    hur
    -0.58
    olerance
    -0.56
    bro
    -0.55
    priced
    -0.54
     Hancock
    -0.54
    POSITIVE LOGITS
     apiece
    0.96
    teen
    0.89
    aciously
    0.79
     ones
    0.78
     others
    0.77
     died
    0.74
     were
    0.73
     succumbed
    0.72
     survived
    0.72
     withdrew
    0.69
    Act Density 0.188%

    No Known Activations