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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating the absence or unavailability of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.75
    WEBPACK
    -0.62
     every
    -0.56
    IndentedString
    -0.56
     instead
    -0.54
    +#+#
    -0.53
     ANCHE
    -0.52
     istället
    -0.51
    Died
    -0.51
     varying
    -0.50
    POSITIVE LOGITS
     neither
    1.76
    neither
    1.63
     Neither
    1.51
    Neither
    1.47
     nici
    1.43
     ninguna
    1.42
     ni
    1.38
     nenhuma
    1.38
     ningún
    1.37
     nenhum
    1.36
    Act Density 0.059%

    No Known Activations