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

    Neuronpedia

    INDEX
    Explanations

    numerical values or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pudding
    -0.72
     performer
    -0.67
     attacker
    -0.63
    amph
    -0.63
     bearer
    -0.62
     recorder
    -0.62
     healer
    -0.61
     kit
    -0.61
     accomplished
    -0.61
     aside
    -0.60
    POSITIVE LOGITS
    5
    1.18
    00
    1.13
    7
    1.10
    0
    1.10
    6
    1.08
    25
    1.08
    8
    1.06
    50
    1.03
    95
    1.03
    06
    1.03
    Act Density 0.073%

    No Known Activations