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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to artistic expression and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iq
    -0.67
     Osc
    -0.65
    ologne
    -0.63
    opian
    -0.62
    iox
    -0.62
    Rated
    -0.62
     Shed
    -0.60
    iken
    -0.59
     Niet
    -0.59
    uma
    -0.59
    POSITIVE LOGITS
    selves
    1.16
    theless
    1.15
    entimes
    1.03
    withstanding
    0.91
    forth
    0.91
    lihood
    0.84
    terday
    0.83
    rely
    0.82
    etheless
    0.78
    FORE
    0.78
    Act Density 0.240%

    No Known Activations