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

    Neuronpedia

    INDEX
    Explanations

    words related to accidents, mishaps, and incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to mishaps or accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -1.08
    anamo
    -0.85
    vernment
    -0.83
    emort
    -0.78
    entin
    -0.78
    netflix
    -0.78
     Enhancement
    -0.74
    elaide
    -0.73
     Panther
    -0.73
    imental
    -0.72
    POSITIVE LOGITS
    sie
    0.90
     mish
    0.87
     Doodle
    0.85
     Mish
    0.84
     mash
    0.77
    apolis
    0.72
    aps
    0.72
    aped
    0.70
    ash
    0.68
    alon
    0.68
    Act Density 0.015%

    No Known Activations