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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to expressing thoughts or ideas clearly and effectively

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "articulate" and related concepts expressing clarity and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bohem
    -0.69
    uden
    -0.66
     Mile
    -0.65
    rentice
    -0.64
     Tycoon
    -0.63
    emade
    -0.62
    atch
    -0.62
     Carbuncle
    -0.61
     Gamble
    -0.60
    opes
    -0.60
    POSITIVE LOGITS
     artic
    1.36
     articulated
    1.08
     articulate
    1.01
    WER
    0.83
    idable
    0.81
    DonaldTrump
    0.79
    Artist
    0.74
     chords
    0.74
    ãĤ¡
    0.71
     eloqu
    0.68
    Act Density 0.014%

    No Known Activations