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

    Neuronpedia

    INDEX
    Explanations

    references to destruction or damage caused by significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    566
    -0.17
    orbit
    -0.15
    HECK
    -0.15
     Toxic
    -0.15
    udi
    -0.14
     Animalia
    -0.14
     toxicity
    -0.13
    ç·ł
    -0.13
    RGB
    -0.13
    739
    -0.13
    POSITIVE LOGITS
    ارت
    0.15
    utenberg
    0.15
    appers
    0.14
    ibar
    0.14
    age
    0.14
    Listing
    0.14
     industri
    0.14
    kok
    0.14
    esion
    0.13
    dia
    0.13
    Act Density 0.047%

    No Known Activations