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

    Neuronpedia

    INDEX
    Explanations

    terms related to lists or collections in a data structure context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.87
     Roskov
    -0.77
    featureID
    -0.75
     nahilalakip
    -0.74
     Meksiku
    -0.72
    iastes
    -0.71
    Datuak
    -0.70
     Италијани
    -0.68
    WebElementEntity
    -0.68
     дописавши
    -0.67
    POSITIVE LOGITS
     vastaan
    0.58
    ⓧ
    0.54
     дъ
    0.50
    ינ
    0.49
     '<?
    0.49
    лоу
    0.49
    gående
    0.49
     mesmos
    0.48
     differently
    0.48
     tarko
    0.47
    Act Density 0.250%

    No Known Activations