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

    Neuronpedia

    INDEX
    Explanations

    adjectives that convey strength and quality

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

    positive descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.65
     EconPapers
    -0.62
     CONTRIBUTION
    -0.54
     CONCEPT
    -0.54
     ProtoMessage
    -0.54
     Jorg
    -0.52
     يتيمه
    -0.49
    concept
    -0.49
     CGRectMake
    -0.49
    aspectj
    -0.47
    POSITIVE LOGITS
     חיצוניים
    0.50
     poffible
    0.48
     pleaſure
    0.45
     faſt
    0.44
     Савезне
    0.43
     fhort
    0.40
     externi
    0.39
     reft
    0.38
    BagLayout
    0.37
     reaſon
    0.37
    Act Density 0.030%

    No Known Activations