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

    Neuronpedia

    INDEX
    Explanations

    superlatives used in comparisons related to different subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize superlatives and rankings across various categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lav
    -0.71
    actionDate
    -0.67
    dl
    -0.64
    potion
    -0.64
    plin
    -0.62
    itent
    -0.62
    velt
    -0.61
    sure
    -0.60
     unfocusedRange
    -0.60
    soft
    -0.59
    POSITIVE LOGITS
    ocating
    0.94
    igator
    0.88
     kinds
    0.87
    igators
    0.83
    udes
    0.80
     proportions
    0.76
     sorts
    0.75
    ogene
    0.73
    usions
    0.73
    uding
    0.71
    Act Density 0.057%

    No Known Activations