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

    Neuronpedia

    INDEX
    Explanations

    titles or headings containing colons

    oai_token-act-pair · gpt-3.5-turbo

    colons and slashes typically used in titles or headings related to media events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jong
    -0.71
     clin
    -0.65
     exerc
    -0.65
     granite
    -0.63
    uku
    -0.62
     breeds
    -0.62
    !--
    -0.62
    aning
    -0.61
     twe
    -0.61
     booster
    -0.61
    POSITIVE LOGITS
    GO
    1.23
    NET
    1.14
    NP
    1.06
    MOD
    0.99
    CAR
    0.99
    ADD
    0.99
    FIN
    0.97
    VERT
    0.97
    PRO
    0.97
    DB
    0.97
    Act Density 0.057%

    No Known Activations