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

    Neuronpedia

    INDEX
    Explanations

    references to snakes or snake-related terms

    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
    estine
    -0.87
    vre
    -0.80
    encer
    -0.76
    amily
    -0.73
    ICAN
    -0.70
    ufact
    -0.67
    sts
    -0.66
    eatures
    -0.65
    VB
    -0.63
    mable
    -0.63
    POSITIVE LOGITS
    bite
    1.24
     snakes
    1.11
     snake
    0.98
     venom
    0.91
    Snake
    0.90
     reptiles
    0.90
     turtles
    0.89
    guards
    0.88
    zilla
    0.84
    oche
    0.80
    Act Density 0.015%

    No Known Activations