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

    Neuronpedia

    INDEX
    Explanations

    words related to criminal activities such as incest, extortion, and blackmail

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illegal or unethical activities involving incest, extortion, and blackmail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ì
    -0.77
    estones
    -0.75
    overy
    -0.74
    çĦ
    -0.74
     Components
    -0.73
     Orchestra
    -0.69
     Coco
    -0.69
    Frames
    -0.69
    ASHINGTON
    -0.68
    cules
    -0.67
    POSITIVE LOGITS
    uous
    1.08
    uously
    0.89
     blackmail
    0.84
    itus
    0.81
    ual
    0.80
    uring
    0.79
    urous
    0.77
    yrinth
    0.74
     taboo
    0.74
     confessions
    0.73
    Act Density 0.011%

    No Known Activations