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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing various concepts, such as good, great, fitting, hard, deeper, easy, and imperfect

    oai_token-act-pair · gpt-3.5-turbo

    sentiments and evaluations related to quality and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selected
    -0.68
     Tripoli
    -0.68
     Hemp
    -0.65
    oided
    -0.64
     Pax
    -0.62
    arcity
    -0.61
    rane
    -0.60
     Nether
    -0.59
     Roche
    -0.58
    rongh
    -0.57
    POSITIVE LOGITS
    âĢ
    1.43
    ðŁ
    1.12
     ðŁij
    1.11
    ðŁĺ
    1.09
    ðŁij
    1.03
    âľ
    1.03
    ¨
    1.02
    âĻ
    1.01
    âĺ
    1.01
    !!!!
    1.00
    Act Density 0.385%

    No Known Activations