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

    Neuronpedia

    INDEX
    Explanations

    references to hazardous materials and safety protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ASIC
    -0.17
    EDITOR
    -0.15
    rawler
    -0.15
    iasi
    -0.14
    rella
    -0.14
    íĥĢ
    -0.14
    COOKIE
    -0.14
    rise
    -0.13
    rippling
    -0.13
    worthy
    -0.13
    POSITIVE LOGITS
     Haz
    0.33
    Haz
    0.32
     hazardous
    0.32
     haz
    0.32
     Hazard
    0.31
     DOT
    0.30
    DOT
    0.28
     hazard
    0.27
     Dangerous
    0.24
     dangerous
    0.23
    Act Density 0.016%

    No Known Activations