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

    Neuronpedia

    INDEX
    Explanations

    phrases related to responsibilities and consequences

    oai_token-act-pair · gpt-3.5-turbo

    modal and auxiliary verbs indicating certainty or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anu
    -0.66
    ft
    -0.66
    aft
    -0.65
     lou
    -0.64
    laus
    -0.64
    oppers
    -0.63
     Hamp
    -0.63
     Hawai
    -0.61
     fishes
    -0.61
    isy
    -0.61
    POSITIVE LOGITS
     actually
    0.93
    ãĤ¦ãĤ¹
    0.84
     probably
    0.83
     exactly
    0.83
     priceless
    0.80
    actly
    0.78
    çī
    0.77
     identical
    0.77
    Ĥİ
    0.76
     awfully
    0.76
    Act Density 0.376%

    No Known Activations