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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "replacing" or "rearranging"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negation or undesirable qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.74
     Wellington
    -0.67
     Warwick
    -0.66
     ribbon
    -0.64
     Solitaire
    -0.61
    STD
    -0.61
     Hawth
    -0.61
     Mayer
    -0.60
     Wonderland
    -0.59
    boxing
    -0.59
    POSITIVE LOGITS
    itiveness
    1.15
    iencies
    1.14
    itive
    1.13
    itions
    1.13
    itely
    1.11
    ishable
    0.99
    atory
    0.95
    utation
    0.95
    ciation
    0.94
    ileged
    0.92
    Act Density 0.069%

    No Known Activations