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

    Neuronpedia

    INDEX
    Explanations

    references to specific topics or elements within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Honor
    -0.17
    orer
    -0.16
    -0.15
     conf
    -0.15
    isto
    -0.15
     different
    -0.15
     подав
    -0.15
     on
    -0.15
     others
    -0.15
     upon
    -0.15
    POSITIVE LOGITS
    žÃŃ
    0.16
    elu
    0.16
     numberWith
    0.16
    TCHA
    0.16
    izedName
    0.15
     nackte
    0.15
    amı
    0.15
    FLOW
    0.14
     Huff
    0.14
    ëŀij
    0.13
    Act Density 0.062%

    No Known Activations