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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "torture" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to torture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.77
     Darkness
    -0.73
     magnification
    -0.73
     Prospect
    -0.70
     IST
    -0.68
     donor
    -0.67
     brightest
    -0.65
     Farn
    -0.65
    è£ħ
    -0.64
     livest
    -0.62
    POSITIVE LOGITS
    urous
    1.44
    oise
    1.40
    illas
    1.14
    eur
    1.14
    ured
    1.06
    uous
    1.03
    urers
    1.03
    imer
    1.02
    uring
    0.99
    oled
    0.99
    Act Density 0.021%

    No Known Activations