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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation used in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hollow
    -0.16
    udoku
    -0.15
    ợi
    -0.15
    ÃŁen
    -0.15
    ص
    -0.15
    osyal
    -0.15
    омеÑĤ
    -0.15
    ÏĪε
    -0.14
    ibling
    -0.14
     же
    -0.14
    POSITIVE LOGITS
    /-
    0.18
    chein
    0.17
    oller
    0.16
    ams
    0.16
    apo
    0.15
    ++++++++++++++++
    0.15
    apol
    0.14
    amp
    0.14
    apos
    0.14
     vanity
    0.14
    Act Density 0.016%

    No Known Activations