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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of certain identifiers or markers in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tsy
    -0.15
     инÑĦоÑĢма
    -0.14
    ContextHolder
    -0.14
    akter
    -0.14
    rün
    -0.14
    oreferrer
    -0.13
     докÑĥм
    -0.13
    AllowAnonymous
    -0.13
    lsru
    -0.13
    abcdefghijkl
    -0.13
    POSITIVE LOGITS
     Castillo
    0.16
     Harm
    0.14
     consc
    0.14
    łģ
    0.14
     Madness
    0.13
     moden
    0.13
    óc
    0.13
     blackmail
    0.13
     Canter
    0.13
    Äı
    0.13
    Act Density 0.000%

    No Known Activations