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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict, removal, and correction

    oai_token-act-pair · gpt-3.5-turbo

    statements about rules or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricanes
    -0.73
     lately
    -0.67
    ©¶æ
    -0.65
     recently
    -0.59
    htaking
    -0.59
     Philips
    -0.58
    ricane
    -0.57
     recent
    -0.56
    stad
    -0.55
    icates
    -0.55
    POSITIVE LOGITS
     accordingly
    0.96
     immediately
    0.84
     automatically
    0.82
    .'"
    0.77
     corresponding
    0.74
    .'
    0.72
    !".
    0.70
    !'"
    0.70
    .","
    0.69
     instantly
    0.69
    Act Density 1.003%

    No Known Activations