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

    Neuronpedia

    INDEX
    Explanations

    superlatives related to people or things that stand out as the best or most significant in their category

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing superlatives and comparisons of greatness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lash
    -0.73
    lav
    -0.71
    ISSION
    -0.68
    isoft
    -0.63
    CHAT
    -0.61
    aird
    -0.59
    cakes
    -0.58
    bed
    -0.58
    dor
    -0.58
    soft
    -0.58
    POSITIVE LOGITS
    ocating
    1.04
    ogene
    0.83
    ometry
    0.81
     sorts
    0.78
     kinds
    0.76
    udes
    0.75
     Invention
    0.70
     imaginable
    0.70
    iance
    0.70
     Mankind
    0.69
    Act Density 0.039%

    No Known Activations