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

    Neuronpedia

    INDEX
    Explanations

    words related to thoughts and responses in discussions or comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elon
    -0.16
    unk
    -0.15
    usted
    -0.14
     æĹ
    -0.14
    ĶĦ
    -0.14
    eras
    -0.13
    oro
    -0.13
    uffman
    -0.13
    infeld
    -0.13
    168
    -0.13
    POSITIVE LOGITS
    -eslint
    0.16
    pla
    0.15
    baÅŁ
    0.15
    borg
    0.14
    folk
    0.14
    oub
    0.14
    -mini
    0.13
    ehr
    0.13
    icas
    0.13
    kers
    0.13
    Act Density 0.004%

    No Known Activations