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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives

    oai_token-act-pair · gpt-3.5-turbo

    comparative and superlative adjectives indicating size, distance, and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IENCE
    -0.75
    ————
    -0.68
    Doctor
    -0.67
    ARA
    -0.66
    ãĥĵ
    -0.63
    uba
    -0.63
    AIDS
    -0.62
    FORE
    -0.62
     Zeal
    -0.62
    ARS
    -0.61
    POSITIVE LOGITS
    hest
    0.83
     portions
    0.68
     estates
    0.67
    iest
    0.67
     sul
    0.67
    liest
    0.66
    most
    0.66
     "$:/
    0.66
    thren
    0.65
    ħĭ
    0.65
    Act Density 0.063%

    No Known Activations