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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflicts and resolutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating consequences or outcomes involving significant implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     earthqu
    -0.71
     unbeliev
    -0.66
    erenn
    -0.61
    bucks
    -0.57
     subur
    -0.56
     Fold
    -0.55
     Lans
    -0.54
    asma
    -0.54
    schild
    -0.54
    sie
    -0.53
    POSITIVE LOGITS
     therefore
    1.06
     consequently
    1.03
     ".
    1.02
     "âĢ¦
    0.99
    ".[
    0.94
     accordingly
    0.93
     "...
    0.91
     thereafter
    0.91
     "[
    0.91
     deserved
    0.90
    Act Density 0.718%

    No Known Activations