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

    Neuronpedia

    INDEX
    Explanations

    Latin characters and symbols such as 'Ļ', 'ľ', 'Ŀ'

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and political themes or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stretched
    -0.82
     perhaps
    -0.75
     marked
    -0.73
     fewer
    -0.72
     maybe
    -0.70
     depressed
    -0.70
     doubtless
    -0.70
     faintly
    -0.69
     isolated
    -0.69
     neither
    -0.69
    POSITIVE LOGITS
    issance
    1.06
    station
    1.00
    formation
    0.98
    education
    0.97
    culosis
    0.96
    ship
    0.95
    cycle
    0.94
    leaders
    0.93
    iversary
    0.93
    rage
    0.93
    Act Density 0.196%

    No Known Activations