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

    Neuronpedia

    INDEX
    Explanations

    quotes and references to sources in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actics
    -0.15
    üçük
    -0.14
    avanaugh
    -0.13
    bens
    -0.13
    uner
    -0.13
    idden
    -0.13
    zet
    -0.13
     kâ
    -0.13
    elerik
    -0.13
    umbnails
    -0.13
    POSITIVE LOGITS
     sources
    1.00
     Sources
    0.84
    sources
    0.80
     source
    0.78
    Sources
    0.75
    source
    0.63
    _sources
    0.61
    -source
    0.59
     Source
    0.57
    .sources
    0.56
    Act Density 0.190%

    No Known Activations