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

    Neuronpedia

    INDEX
    Explanations

    words related to curses and hexes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "curse" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.85
    arger
    -0.81
    nington
    -0.80
    Goal
    -0.79
    visors
    -0.79
    arnaev
    -0.78
    atican
    -0.75
    olitan
    -0.73
    unicip
    -0.72
     GOODMAN
    -0.70
    POSITIVE LOGITS
     curse
    1.10
     curses
    0.91
     cursed
    0.90
     cursing
    0.89
     cringe
    0.73
    vine
    0.73
     destro
    0.72
    hammer
    0.72
     scourge
    0.71
    fully
    0.71
    Act Density 0.009%

    No Known Activations