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

    Neuronpedia

    INDEX
    Explanations

    specific references or instances described as examples or illustrations

    oai_token-act-pair · gpt-3.5-turbo

    instances of "case in point" or references to specific examples or cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chy
    -0.76
    hirt
    -0.74
    soDeliveryDate
    -0.71
    chie
    -0.65
    iami
    -0.63
    PASS
    -0.62
    ãĥ¥
    -0.62
    omething
    -0.62
    ãĥı
    -0.62
    ulous
    -0.60
    POSITIVE LOGITS
    ĪĴ
    0.64
     particulars
    0.62
    otics
    0.58
    study
    0.57
     arms
    0.56
    lambda
    0.53
     Rohingya
    0.52
     point
    0.52
    alis
    0.50
     Soup
    0.50
    Act Density 0.113%

    No Known Activations