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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific titles of shows or films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dot
    -0.15
    hausen
    -0.15
    ç¯
    -0.14
    γÏĮ
    -0.14
    омÑĸ
    -0.14
    hem
    -0.14
     ZEND
    -0.14
    ULE
    -0.14
    esktop
    -0.14
    añ
    -0.13
    POSITIVE LOGITS
    ahoo
    0.16
    erring
    0.15
    éºĹ
    0.14
    idders
    0.14
    ibble
    0.14
    ụ
    0.14
    ÑĥмÑĥ
    0.14
    qus
    0.14
    ERA
    0.14
    ienia
    0.14
    Act Density 0.020%

    No Known Activations