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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the determination of status or justification in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     سكانية
    -0.52
    writeField
    -0.50
     kaarangay
    -0.47
     gouttes
    -0.47
     Италијани
    -0.46
    новништво
    -0.45
    лтамалар
    -0.44
     Kishi
    -0.44
    PreferredItem
    -0.43
    ngdoc
    -0.43
    POSITIVE LOGITS
     many
    0.78
     numerous
    0.71
     dozens
    0.67
    many
    0.64
     hundreds
    0.63
     nearly
    0.62
     thousands
    0.59
     several
    0.59
     banyak
    0.57
     lots
    0.57
    Act Density 0.720%

    No Known Activations