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

    Neuronpedia

    INDEX
    Explanations

    the word "debate" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to "debate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meal
    -0.73
     guiActiveUnfocused
    -0.72
    ĸļ
    -0.72
     Inquisitor
    -0.71
     Cth
    -0.71
     Siberian
    -0.71
    MIC
    -0.66
    velt
    -0.65
    MpServer
    -0.62
    coni
    -0.62
    POSITIVE LOGITS
    ilit
    1.10
    atable
    1.08
    ilitation
    1.07
    ounced
    1.01
    utations
    0.97
    uted
    0.97
    unker
    0.97
    ased
    0.96
    utation
    0.96
    atri
    0.92
    Act Density 0.012%

    No Known Activations