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

    Neuronpedia

    INDEX
    Explanations

    snakes or references related to snakes in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of snakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´ãĤ¡
    -0.86
    estine
    -0.77
    ãĥĨãĤ£
    -0.72
    ICAN
    -0.68
    âĸ¬
    -0.67
     WARN
    -0.64
    supp
    -0.64
     Prob
    -0.64
    riel
    -0.63
    ces
    -0.62
    POSITIVE LOGITS
     snakes
    1.34
     snake
    1.28
     reptiles
    1.03
    bite
    1.02
     turtles
    1.01
     venom
    0.98
     Snake
    0.90
    Snake
    0.88
    ulic
    0.84
     crocod
    0.84
    Act Density 0.009%

    No Known Activations