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

    Neuronpedia

    INDEX
    Explanations

    references to the pronoun 'you'

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ItemModel
    -0.72
    mian
    -0.71
     yourself
    -0.68
    mable
    -0.64
    ciel
    -0.63
    olen
    -0.61
    mentar
    -0.60
    født
    -0.59
    chymal
    -0.58
     Bennet
    -0.58
    POSITIVE LOGITS
     endregion
    0.75
     isNameExpr
    0.71
     monographs
    0.69
     alimentaria
    0.68
     tertawa
    0.68
     interactiva
    0.68
    siąż
    0.67
     Babylonian
    0.66
     recomiendo
    0.66
     raiſ
    0.66
    Act Density 0.025%

    No Known Activations