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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives related to weight, color, sound, and temperature

    oai_token-act-pair · gpt-3.5-turbo

    terms related to varying degrees of lightness and heaviness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EP
    -0.77
    este
    -0.74
    ainted
    -0.73
    shire
    -0.72
    odor
    -0.72
    anova
    -0.69
    ette
    -0.69
    eno
    -0.68
    Ward
    -0.68
    advertising
    -0.68
    POSITIVE LOGITS
     than
    1.69
     Than
    1.46
    than
    1.39
     "$:/
    0.94
     versions
    0.85
    iating
    0.77
     ado
    0.74
    anguage
    0.74
    ModLoader
    0.73
     millenn
    0.69
    Act Density 0.062%

    No Known Activations