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

    Neuronpedia

    INDEX
    Explanations

    references to prizes or awards

    oai_token-act-pair · gpt-3.5-turbo

    references to awards or prizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.99
    schild
    -0.68
     HELL
    -0.68
     layer
    -0.64
     bracelet
    -0.64
    ãģ®å®
    -0.62
     layers
    -0.61
     Syd
    -0.61
     LEVEL
    -0.60
    å°Ĩ
    -0.60
    POSITIVE LOGITS
    ests
    1.24
    zes
    1.24
    vy
    1.15
    etary
    1.15
    eta
    1.05
    zed
    1.00
    vet
    0.98
    ety
    0.98
    ory
    0.98
    angular
    0.95
    Act Density 0.014%

    No Known Activations