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

    Neuronpedia

    INDEX
    Explanations

    specific non-English characters and encoding errors

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may represent encoding issues in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oids
    -0.82
    apsed
    -0.77
    enegger
    -0.76
    oidal
    -0.75
    oted
    -0.70
    APS
    -0.69
    idious
    -0.68
     Swordsman
    -0.67
    eners
    -0.67
    oid
    -0.66
    POSITIVE LOGITS
    âĤ¬
    1.20
    ´
    0.96
    ¯
    0.95
    tre
    0.91
    ¸
    0.89
    ¯¯
    0.89
    ï
    0.87
    â
    0.85
    ©
    0.83
    \\\\
    0.83
    Act Density 0.018%

    No Known Activations