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

    Neuronpedia

    INDEX
    Explanations

    adverbs and descriptors that indicate frequency or degree

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

    preceding adverbs of degree

    np_acts-logits-general · gemini-2.0-flash

    comparative degree or emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.67
    bootstrapcdn
    -0.61
     Roskov
    -0.60
    orteur
    -0.58
     demais
    -0.55
    ItemBackground
    -0.55
    ніципалі
    -0.54
     kaynağından
    -0.54
     Référence
    -0.53
     attravers
    -0.52
    POSITIVE LOGITS
    ".
    0.80
     successful
    0.77
     significant
    0.76
     unique
    0.75
     unusual
    0.74
    "):
    0.73
     ')
    0.72
    '):
    0.70
     sizable
    0.70
     famous
    0.69
    Act Density 0.354%

    No Known Activations