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

    Neuronpedia

    INDEX
    Explanations

    references to classification or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ñĥж
    -0.15
    æĿľ
    -0.15
    .us
    -0.15
    %n
    -0.15
    iew
    -0.14
    rael
    -0.14
    ibble
    -0.14
    ìĤ°
    -0.14
    otonin
    -0.14
     Sanford
    -0.13
    POSITIVE LOGITS
    alık
    0.14
     Cunning
    0.14
    aber
    0.14
    åľ¨åľ°
    0.14
    OperationException
    0.14
    unately
    0.13
    utenberg
    0.13
    zing
    0.13
    egra
    0.13
     Gel
    0.13
    Act Density 0.036%

    No Known Activations