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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate lists or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.16
    ofil
    -0.14
    еÑĨÑĤ
    -0.14
    _isr
    -0.14
    hua
    -0.14
    unte
    -0.13
     Commentary
    -0.13
    ingles
    -0.13
    llum
    -0.13
    dden
    -0.13
    POSITIVE LOGITS
     example
    0.22
     list
    0.19
     exemple
    0.19
    example
    0.18
     tip
    0.17
     link
    0.16
    /lists
    0.16
     sample
    0.16
     Link
    0.15
    /link
    0.15
    Act Density 0.079%

    No Known Activations