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

    Neuronpedia

    INDEX
    Explanations

    references to a fictional location named "Hell"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Hell"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.85
    è¿
    -0.74
    æī
    -0.71
    NRS
    -0.69
    æĸ¹
    -0.68
    æ°
    -0.68
    Decre
    -0.67
    00000
    -0.67
    APD
    -0.67
    PsyNetMessage
    -0.66
    POSITIVE LOGITS
    enic
    1.17
    hound
    0.97
    ibur
    0.88
    cats
    0.86
    ishly
    0.85
    anger
    0.84
    ocaust
    0.80
    bender
    0.80
    hell
    0.80
     Hell
    0.79
    Act Density 0.007%

    No Known Activations