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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms or governmental actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restrictions or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.78
    FORE
    -0.67
    >>>>
    -0.67
     Samoa
    -0.61
     Corsair
    -0.60
     promise
    -0.58
     salv
    -0.58
     exha
    -0.57
     heck
    -0.56
     Khe
    -0.55
    POSITIVE LOGITS
    rict
    1.15
    ombat
    1.00
    cliffe
    0.91
    ional
    0.89
    ions
    0.88
    abulary
    0.86
    ory
    0.84
    rait
    0.84
    iveness
    0.83
    riad
    0.83
    Act Density 0.018%

    No Known Activations