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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve accidents and injuries in public spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    иÑĤоÑĢ
    -0.17
    ONSE
    -0.16
    ãĥ¼ãĥĢ
    -0.16
     ÑĦеÑĢ
    -0.15
    IMA
    -0.15
    /WebAPI
    -0.14
    aney
    -0.14
    FG
    -0.14
    ">ÃĹ</
    -0.14
    ignon
    -0.14
    POSITIVE LOGITS
     fall
    0.33
     falls
    0.31
    fall
    0.27
     falling
    0.26
     Falls
    0.26
     fallen
    0.25
     fell
    0.24
     Fall
    0.24
     FALL
    0.23
    Fall
    0.23
    Act Density 0.077%

    No Known Activations