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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to authors or contributors in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otch
    -0.17
    adal
    -0.16
    .opend
    -0.15
    otech
    -0.15
    panic
    -0.14
    adelphia
    -0.14
    ctxt
    -0.14
     Hatch
    -0.14
    akan
    -0.14
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.14
    POSITIVE LOGITS
    ãĥ£
    0.15
     pé
    0.14
    Tip
    0.14
    ä½Ļ
    0.14
    onyms
    0.14
     Charter
    0.14
     peÅŁ
    0.13
    AE
    0.13
    äh
    0.13
     charter
    0.13
    Act Density 0.090%

    No Known Activations