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

    Neuronpedia

    INDEX
    Explanations

    references to time periods and categorizations of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.19
    inka
    -0.16
    alytics
    -0.15
    -archive
    -0.14
    aling
    -0.14
    ذر
    -0.14
    ilenames
    -0.14
    dojo
    -0.14
    оваÑĢ
    -0.14
    íģ
    -0.14
    POSITIVE LOGITS
     fled
    0.15
    lice
    0.15
     itemprop
    0.15
    ocrats
    0.15
    env
    0.14
     Wildlife
    0.14
    ogen
    0.14
    uger
    0.14
     dis
    0.14
     Rug
    0.14
    Act Density 0.005%

    No Known Activations