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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal issues and statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal issues and existential questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ
    -1.03
    ''.
    -0.94
    Others
    -0.87
    .''
    -0.83
    .''.
    -0.79
    ?ãĢį
    -0.77
    âĸł
    -0.77
     âĢ
    -0.76
    )\
    -0.76
    ÂŃ
    -0.75
    POSITIVE LOGITS
     EVERY
    1.05
     HUGE
    0.99
     VERY
    0.92
     absolutely
    0.84
     ONLY
    0.83
     ALL
    0.81
     NEVER
    0.80
     ALWAYS
    0.77
     NOT
    0.77
     REALLY
    0.73
    Act Density 2.113%

    No Known Activations