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

    Neuronpedia

    INDEX
    Explanations

    the presence of comments or annotations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sock
    -0.15
    atoi
    -0.14
    SEA
    -0.14
    omes
    -0.14
     åĢ
    -0.13
    izza
    -0.13
    SIM
    -0.13
    overy
    -0.13
    egg
    -0.13
    baar
    -0.13
    POSITIVE LOGITS
    uden
    0.16
    imed
    0.15
    aland
    0.14
    msgid
    0.14
     Dawson
    0.14
    ichten
    0.14
    oken
    0.14
     bon
    0.14
     prom
    0.14
     incap
    0.13
    Act Density 0.019%

    No Known Activations