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

    Neuronpedia

    INDEX
    Explanations

    organizations, countries, political parties, and variables mentioned in the context

    oai_token-act-pair · gpt-3.5-turbo

    references to political or organizational entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Newsletter
    -0.70
    ogle
    -0.69
    utory
    -0.67
    nen
    -0.64
    lé
    -0.63
    =-=-
    -0.62
     Dud
    -0.61
    nce
    -0.59
    trial
    -0.57
    pter
    -0.56
    POSITIVE LOGITS
     sexes
    1.08
     equally
    0.90
     halves
    0.88
     simultaneously
    0.87
    ieth
    0.84
     sides
    0.82
     alike
    0.78
     SLI
    0.77
     individually
    0.76
     extremes
    0.75
    Act Density 0.151%

    No Known Activations