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

    Neuronpedia

    INDEX
    Explanations

    expressions related to assessment and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    discussions of legal consequences and policy implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chili
    -0.68
    bara
    -0.63
    da
    -0.62
     Trailer
    -0.61
     Bord
    -0.61
    Soc
    -0.61
     Vive
    -0.61
     Fortune
    -0.59
     este
    -0.59
    mosp
    -0.58
    POSITIVE LOGITS
     themselves
    0.98
     collectively
    0.93
     individually
    0.91
    ensitive
    0.73
     systematically
    0.73
    geries
    0.71
     jointly
    0.70
     constitute
    0.70
     include
    0.69
     originate
    0.69
    Act Density 0.962%

    No Known Activations