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

    Neuronpedia

    INDEX
    Explanations

    linguistic elements associated with South Asian languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.40
     nakalista
    -0.79
    contentLoaded
    -0.77
     intptr
    -0.76
    windowFixed
    -0.74
    isContained
    -0.73
     wireType
    -0.73
    fromnode
    -0.73
    Chham
    -0.72
    IsContent
    -0.71
    POSITIVE LOGITS
     disagre
    1.76
     unlaw
    1.71
     affor
    1.69
     increa
    1.67
     maneu
    1.61
     inappro
    1.59
     impra
    1.59
     hairc
    1.58
     shenan
    1.54
     milf
    1.54
    Act Density 0.030%

    No Known Activations