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

    Neuronpedia

    INDEX
    Explanations

    references to sources or citations in academic or formal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nder
    -0.17
    erap
    -0.16
    ма
    -0.15
    Æ°Æ¡ng
    -0.14
    rotch
    -0.14
    erosis
    -0.14
     Wake
    -0.14
    ÄĻż
    -0.14
    halb
    -0.13
    Wake
    -0.13
    POSITIVE LOGITS
     Rol
    0.14
    bling
    0.14
    ¢
    0.14
    é¡¿
    0.14
    Verb
    0.14
    оже
    0.14
    opsy
    0.14
    tel
    0.14
    олж
    0.14
    uibModal
    0.14
    Act Density 0.036%

    No Known Activations