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

    Neuronpedia

    INDEX
    Explanations

    physical measurements, particularly height and weight

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decor
    -0.64
    oÄŁ
    -0.63
     Lank
    -0.59
    raints
    -0.57
     NEVER
    -0.56
    ctors
    -0.56
    uay
    -0.56
    vous
    -0.56
    uras
    -0.55
     hood
    -0.55
    POSITIVE LOGITS
     apiece
    1.00
     behest
    0.88
    38
    0.77
    0000000
    0.76
     ripe
    0.74
     discretion
    0.73
    34
    0.73
    41
    0.72
    54
    0.72
     expense
    0.72
    Act Density 0.130%

    No Known Activations