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

    Neuronpedia

    INDEX
    Explanations

    phrases related to defiance or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opposition or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.96
    warts
    -0.79
    acons
    -0.70
    asking
    -0.70
    among
    -0.67
    groups
    -0.66
     bridges
    -0.64
    comes
    -0.63
    incinn
    -0.61
    antly
    -0.61
    POSITIVE LOGITS
     norm
    0.71
     customary
    0.70
    Record
    0.66
     usual
    0.63
     gestation
    0.62
    record
    0.61
     record
    0.61
     expectation
    0.60
     reckoning
    0.60
    Ļ½
    0.60
    Act Density 0.485%

    No Known Activations