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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "rid" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ridiculous."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.74
    arser
    -0.66
    avorite
    -0.65
    astern
    -0.64
     sustaining
    -0.61
    HAEL
    -0.60
     councillors
    -0.59
    ploma
    -0.58
    perty
    -0.58
     Kimmel
    -0.57
    POSITIVE LOGITS
    ging
    1.05
    ged
    1.04
    gements
    1.03
    gew
    1.01
    uction
    0.99
    der
    0.99
    uces
    0.99
    gement
    0.98
    gewater
    0.97
    gments
    0.94
    Act Density 0.027%

    No Known Activations