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

    Neuronpedia

    INDEX
    Explanations

    web links or URLs in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or references to significant statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fencing
    -0.74
    istry
    -0.68
     Kass
    -0.66
     cart
    -0.65
     wagon
    -0.62
     Zucker
    -0.62
     Lama
    -0.61
     Zo
    -0.61
     vel
    -0.61
     Ging
    -0.61
    POSITIVE LOGITS
    120
    0.95
    0000000
    0.92
    125
    0.86
    114
    0.86
    157
    0.86
    145
    0.85
    147
    0.85
    148
    0.85
    118
    0.85
    146
    0.85
    Act Density 0.145%

    No Known Activations