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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols associated with proper nouns or significant identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungan
    -0.16
    lund
    -0.14
    crate
    -0.14
     Mandal
    -0.14
    aza
    -0.14
    olland
    -0.14
    readcr
    -0.14
    ledge
    -0.13
     exploitation
    -0.13
    beck
    -0.13
    POSITIVE LOGITS
     crown
    0.16
    аниÑĨ
    0.15
    eÄį
    0.14
     himself
    0.14
     initially
    0.13
    è¥
    0.13
     Princess
    0.13
     commission
    0.13
    edd
    0.13
    anmar
    0.13
    Act Density 0.003%

    No Known Activations