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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mathematical equality and comparison

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IsContent
    -0.79
    Hochspringen
    -0.74
     disambiguazione
    -0.74
     Offisielt
    -0.72
    脚注の使い方
    -0.71
    ulongan
    -0.68
    */;
    -0.68
     تضيفلها
    -0.67
     beginnetje
    -0.67
    ništ
    -0.66
    POSITIVE LOGITS
    (
    0.53
    ribune
    0.52
    SequentialGroup
    0.52
    yarnpkg
    0.52
    [toxicity=0]
    0.52
    adaptiveStyles
    0.51
    :
    0.51
    InstanceState
    0.50
            
    0.49
    forName
    0.48
    Act Density 0.065%

    No Known Activations