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

    Neuronpedia

    INDEX
    Explanations

    incidents related to emergencies or accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.16
    ocale
    -0.15
    íķ
    -0.15
    ember
    -0.15
    oise
    -0.15
    asca
    -0.14
    steam
    -0.14
    pling
    -0.14
     Chow
    -0.14
    owski
    -0.14
    POSITIVE LOGITS
    kke
    0.22
     suspicious
    0.18
     suspected
    0.18
     suspect
    0.17
     possibly
    0.16
    orf
    0.16
     potentially
    0.15
     suspects
    0.15
    åł
    0.15
     taxation
    0.15
    Act Density 0.113%

    No Known Activations