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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Демографія
    -0.82
     CWE
    -0.82
     HttpNotFound
    -0.71
    ."</
    -0.70
     Tiong
    -0.69
    ṯ
    -0.69
     Rowley
    -0.69
    {{/
    -0.66
    DataContract
    -0.66
    ="/">
    -0.65
    POSITIVE LOGITS
    äsident
    0.60
    $\
    0.59
     excès
    0.58
     Kent
    0.58
     Gabe
    0.58
    Kent
    0.57
    culaires
    0.56
    erráneo
    0.56
    $
    0.56
     Saltar
    0.56
    Act Density 0.179%

    No Known Activations