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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to duality or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.73
    Ĥª
    -0.69
    ŃĶ
    -0.67
    ©¶æ¥µ
    -0.62
    @#
    -0.60
    depending
    -0.55
    .",
    -0.54
    taboola
    -0.53
    .).
    -0.53
     anytime
    -0.52
    POSITIVE LOGITS
     and
    1.11
     AND
    0.97
     versus
    0.85
     nor
    0.81
    and
    0.71
     vs
    0.70
     &
    0.58
     sexes
    0.57
     And
    0.56
    athed
    0.56
    Act Density 0.485%

    No Known Activations