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

    Neuronpedia

    INDEX
    Explanations

    informal and vague references to miscellaneous items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    both
    -0.53
     both
    -0.48
     Ebenso
    -0.46
    程
    -0.44
     par
    -0.43
    ArgsConstructor
    -0.42
     vra
    -0.41
    cest
    -0.41
    みましょう
    -0.41
    :_
    -0.41
    POSITIVE LOGITS
    ########.
    0.89
    queryInterface
    0.78
    expandindo
    0.76
    ftagPool
    0.73
     stuff
    0.72
     semacam
    0.71
    ⓧ
    0.71
    dziew
    0.67
     []:
    0.66
    Бележки
    0.66
    Act Density 0.325%

    No Known Activations