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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Yaobang" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ————————————————
    -0.82
    ãĥĩãĤ£
    -0.78
    aneous
    -0.77
    Oracle
    -0.75
    mented
    -0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.71
    rative
    -0.69
    cons
    -0.68
    Runtime
    -0.67
    aneously
    -0.66
    POSITIVE LOGITS
     Ya
    1.20
     tremend
    0.82
    vana
    0.82
    emonic
    0.78
    ollah
    0.77
    akov
    0.77
    alon
    0.75
     Bulg
    0.75
    nect
    0.74
    ÅĤ
    0.74
    Act Density 0.012%

    No Known Activations