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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    not quite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mahdollis
    -0.35
    StructEnd
    -0.34
    çalves
    -0.32
     randomly
    -0.31
     apapun
    -0.31
    erschied
    -0.30
     anything
    -0.29
     Archiproducts
    -0.29
     only
    -0.29
    sspiel
    -0.29
    POSITIVE LOGITS
    quite
    0.71
     Quite
    0.70
    Quite
    0.69
     quite
    0.66
    KommentareTeilen
    0.63
     autorytatywna
    0.60
     betweenstory
    0.54
    URLException
    0.52
     للمعارف
    0.52
     laſſen
    0.52
    Act Density 0.008%

    No Known Activations