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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovic
    -0.15
    ãĥ¼ãĤº
    -0.14
    serializer
    -0.14
     Hast
    -0.13
    Ì
    -0.13
    peg
    -0.13
    ante
    -0.13
     ç¯
    -0.13
    ero
    -0.13
    pan
    -0.13
    POSITIVE LOGITS
    ">//
    0.19
    rench
    0.15
    platz
    0.15
    axter
    0.14
    عت
    0.14
    åĶ¯
    0.14
    ÑĨÑĮ
    0.14
    isson
    0.14
    ensor
    0.14
    urch
    0.14
    Act Density 0.018%

    No Known Activations