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

    Neuronpedia

    INDEX
    Explanations

    variations of the suffix "-ize" or "-ise" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipa
    -0.16
    avian
    -0.15
    _closed
    -0.15
    frog
    -0.15
    vern
    -0.15
    IGN
    -0.15
    nez
    -0.15
    quate
    -0.15
    FLICT
    -0.14
    clid
    -0.14
    POSITIVE LOGITS
     Ellison
    0.17
    aldi
    0.17
    aldo
    0.16
    quier
    0.16
    bit
    0.15
    gard
    0.15
    ald
    0.15
    ière
    0.15
    .schedulers
    0.14
    iera
    0.14
    Act Density 0.045%

    No Known Activations