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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns that are likely associated with names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     condoms
    -0.69
     Carnage
    -0.68
     Sno
    -0.68
     foreseeable
    -0.67
     Hades
    -0.66
     civilian
    -0.65
     socks
    -0.64
     Pegasus
    -0.64
     mounts
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    POSITIVE LOGITS
    ultz
    1.03
    rick
    0.96
    arnaev
    0.94
    ucci
    0.94
    undy
    0.94
    anmar
    0.94
    alin
    0.93
    orsi
    0.91
    essel
    0.91
    iggs
    0.91
    Act Density 0.108%

    No Known Activations