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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wand
    -0.16
    fila
    -0.15
    hood
    -0.15
    appa
    -0.15
    kovi
    -0.15
     Pikachu
    -0.15
    ilib
    -0.14
    fak
    -0.14
     воÑĤ
    -0.14
    umba
    -0.14
    POSITIVE LOGITS
    -CN
    0.15
    onde
    0.15
    ModelProperty
    0.14
    racat
    0.14
     Pou
    0.14
     menn
    0.14
    .slim
    0.14
    :///
    0.14
    ainen
    0.14
    etur
    0.14
    Act Density 0.003%

    No Known Activations