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

    Neuronpedia

    INDEX
    Explanations

    phrases related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing recommendations or obligations regarding laws and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remnants
    -0.57
    ontent
    -0.57
     Hilbert
    -0.54
     Solitaire
    -0.54
     incomplete
    -0.54
    atz
    -0.54
    etz
    -0.54
     streak
    -0.53
    chu
    -0.53
     Wrath
    -0.52
    POSITIVE LOGITS
     ASAP
    1.21
     urgently
    0.84
     someday
    0.77
    instead
    0.77
     sooner
    0.77
     ideally
    0.76
     foremost
    0.74
     precedence
    0.74
     ashamed
    0.73
     accordingly
    0.71
    Act Density 0.360%

    No Known Activations