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

    Neuronpedia

    INDEX
    Explanations

    variations of the suffix '-er' and related morphological forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.41
    ed
    -0.29
    o
    -0.29
    ois
    -0.25
    m
    -0.25
    y
    -0.25
    oj
    -0.24
    al
    -0.24
    aus
    -0.23
    mars
    -0.22
    POSITIVE LOGITS
    cury
    0.18
    usalem
    0.18
    an
    0.17
    fault
    0.16
    ounter
    0.15
    anja
    0.15
    ิà¸į
    0.15
    keley
    0.15
    ived
    0.14
    ksen
    0.14
    Act Density 0.076%

    No Known Activations