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

    Neuronpedia

    INDEX
    Explanations

    words related to legal terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix 'ation'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herty
    -0.78
    inav
    -0.69
    glers
    -0.68
    tails
    -0.65
    ãĤ©
    -0.65
    izont
    -0.64
    nov
    -0.64
    ãĥĥãĥī
    -0.62
    rimp
    -0.61
    acters
    -0.61
    POSITIVE LOGITS
    ary
    1.13
    ally
    1.08
    hower
    1.00
    naire
    0.99
    arily
    0.95
    ist
    0.90
    ists
    0.89
    SHIP
    0.82
    eering
    0.82
    eer
    0.81
    Act Density 0.054%

    No Known Activations