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

    Neuronpedia

    INDEX
    Explanations

    statements indicating fairness, similarity, or comparison

    oai_token-act-pair · gpt-3.5-turbo

    the word "equally" and its various usages throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.73
     Coff
    -0.73
    liest
    -0.71
     Canaver
    -0.68
    ocene
    -0.65
     Encyclopedia
    -0.63
     Fry
    -0.62
    gest
    -0.62
     Landing
    -0.62
     Buy
    -0.61
    POSITIVE LOGITS
     spaced
    0.97
     weighted
    0.90
     situated
    0.89
    imilar
    0.88
     sized
    0.87
     adept
    0.80
    inguishable
    0.78
     applicable
    0.77
     opposed
    0.74
     ruthless
    0.72
    Act Density 0.026%

    No Known Activations