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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific terminology related to health and research topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.86
    c
    -0.80
    iness
    -0.79
    w
    -0.78
    est
    -0.75
    ings
    -0.75
    y
    -0.73
     Ches
    -0.73
    f
    -0.68
    Y
    -0.67
    POSITIVE LOGITS
     myſelf
    1.40
     themſelves
    1.29
     itſelf
    1.23
     himſelf
    1.13
     becauſe
    1.09
    BibitemShut
    1.07
     ſeveral
    1.07
    ^(@)
    1.04
    olesale
    1.04
    bibfield
    1.03
    Act Density 0.733%

    No Known Activations