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

    Neuronpedia

    INDEX
    Explanations

    mentions of events or situations indicating prohibition, refusal, or restriction

    oai_token-act-pair · gpt-3.5-turbo

    instances of attendance and participation in events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggles
    -0.75
    icult
    -0.73
    perfect
    -0.73
    loo
    -0.73
     somew
    -0.72
    cellent
    -0.70
    stellar
    -0.70
     wonderfully
    -0.69
     tremend
    -0.68
     terrific
    -0.68
    POSITIVE LOGITS
     anymore
    1.66
     nor
    1.38
     any
    1.24
     anything
    1.16
     unless
    1.12
     anyone
    1.02
     whatsoever
    0.96
     anybody
    0.96
     ANY
    0.90
     anytime
    0.88
    Act Density 0.461%

    No Known Activations