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

    Neuronpedia

    INDEX
    Explanations

    mentions of reptiles, particularly snakes

    oai_token-act-pair · gpt-3.5-turbo

    references to snakes and snake-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estine
    -0.80
    vre
    -0.76
    encer
    -0.68
    eatures
    -0.67
     Beckham
    -0.66
    sts
    -0.64
     Neh
    -0.63
    ufact
    -0.62
     propos
    -0.62
     Universal
    -0.62
    POSITIVE LOGITS
    bite
    1.17
     snakes
    1.07
    guards
    0.93
     snake
    0.92
    Snake
    0.91
     venom
    0.85
    atos
    0.84
    opus
    0.83
    oche
    0.83
     reptiles
    0.81
    Act Density 0.018%

    No Known Activations