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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocaly
    -0.17
    vert
    -0.16
    usher
    -0.16
    imates
    -0.15
    ensed
    -0.15
    ires
    -0.15
    USH
    -0.15
     Kiss
    -0.15
    ainter
    -0.14
    enton
    -0.14
    POSITIVE LOGITS
    ä
    0.20
    ie
    0.18
     Rena
    0.17
    ãĥĥãĥĦ
    0.17
    iez
    0.17
    Hang
    0.16
    ëį°ìĿ´íĬ¸
    0.16
    246
    0.16
    onne
    0.16
     Hang
    0.15
    Act Density 0.030%

    No Known Activations