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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing intensity or positive evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.67
     ſind
    -0.59
     Italijani
    -0.57
     الحره
    -0.57
    MLLoader
    -0.56
    localctx
    -0.55
    الحياه
    -0.55
     Chwiliwch
    -0.50
     كومونز
    -0.49
    WithIOException
    -0.49
    POSITIVE LOGITS
     Very
    1.63
    Very
    1.48
    Nice
    1.18
     Excellent
    1.17
    Excellent
    1.16
     Nice
    1.14
    Wonderful
    1.08
    Lovely
    1.08
     Extremely
    1.07
     Amazing
    1.04
    Act Density 0.182%

    No Known Activations