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

    Neuronpedia

    INDEX
    Explanations

    comparisons between quantities or qualities

    oai_token-act-pair · gpt-3.5-turbo

    comparative concepts related to size, quantity, and demographic differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escription
    -0.62
    estern
    -0.61
     reluct
    -0.59
    DragonMagazine
    -0.57
    ãĥĻ
    -0.57
    hea
    -0.56
    gradient
    -0.56
    oken
    -0.55
    details
    -0.54
     immunity
    -0.54
    POSITIVE LOGITS
     combined
    1.03
     ever
    0.96
     anymore
    0.83
     nor
    0.81
    average
    0.77
     admit
    0.77
     existed
    0.76
    ().
    0.75
     counterparts
    0.75
     EVER
    0.74
    Act Density 0.233%

    No Known Activations