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

    Neuronpedia

    INDEX
    Explanations

    words related to constraints, restrictions, and limits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restrictions and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sham
    -0.81
    roma
    -0.78
    ublic
    -0.75
    姫
    -0.73
    fort
    -0.70
    itely
    -0.70
     Psychiat
    -0.69
    earth
    -0.68
    DragonMagazine
    -0.67
    ands
    -0.66
    POSITIVE LOGITS
     access
    1.08
     liability
    1.01
     allowable
    0.97
     how
    0.95
     freedoms
    0.89
     permissible
    0.86
     exposure
    0.86
     withdrawals
    0.86
     availability
    0.85
     eligibility
    0.84
    Act Density 0.081%

    No Known Activations