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

    Neuronpedia

    INDEX
    Explanations

    incidents involving casualties and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹ²
    -0.15
     Fist
    -0.15
    anders
    -0.14
    nces
    -0.14
    ıl
    -0.14
    inters
    -0.14
    soever
    -0.14
    dere
    -0.14
    past
    -0.13
    icare
    -0.13
    POSITIVE LOGITS
     innocent
    0.16
    å§ĵ
    0.15
     swe
    0.15
     Swe
    0.14
    enames
    0.14
    ÄĽÅ¾
    0.14
    urn
    0.14
    antidad
    0.14
     pán
    0.14
    eral
    0.14
    Act Density 0.074%

    No Known Activations