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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing opinions and evaluations of products or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gur
    -0.75
    ogenesis
    -0.74
    IAS
    -0.73
    rir
    -0.70
    racuse
    -0.66
    foreseen
    -0.65
    bia
    -0.65
    lehem
    -0.65
    alysed
    -0.64
    rants
    -0.64
    POSITIVE LOGITS
     standalone
    0.96
     versatile
    0.96
     product
    0.95
     alternative
    0.90
     companion
    0.88
     addition
    0.85
     wearable
    0.82
     everyday
    0.82
     complementary
    0.81
     lightweight
    0.81
    Act Density 0.669%

    No Known Activations