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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or titles related to individuals or characters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "man"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAST
    -0.77
    ritical
    -0.76
    irtual
    -0.74
    rss
    -0.73
    ¥ŀ
    -0.73
    iesel
    -0.72
    ython
    -0.71
    daily
    -0.71
    insured
    -0.70
     Seym
    -0.70
    POSITIVE LOGITS
    hunt
    1.22
    hood
    1.13
    gling
    0.98
    uscript
    0.94
    volent
    0.92
    liness
    0.90
    agers
    0.90
    ifest
    0.89
    liest
    0.88
    nered
    0.81
    Act Density 0.061%

    No Known Activations