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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases involving choices or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.61
    참고
    -0.59
    sidemargin
    -0.54
    itinéraire
    -0.51
     gegeben
    -0.48
     highlights
    -0.48
    titleMargin
    -0.45
     toki
    -0.44
    出版年
    -0.44
     aldus
    -0.42
    POSITIVE LOGITS
     else
    0.90
    Otherwise
    0.82
    protoimpl
    0.81
    Else
    0.80
     Otherwise
    0.78
    наче
    0.78
    elif
    0.77
    otherwise
    0.74
     Else
    0.74
     otherwise
    0.72
    Act Density 0.239%

    No Known Activations