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

    Neuronpedia

    INDEX
    Explanations

    different forms of plural nouns and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erver
    -0.34
    ox
    -0.33
    et
    -0.33
    oft
    -0.32
    oz
    -0.31
    och
    -0.31
    of
    -0.29
    ov
    -0.28
    um
    -0.28
    hip
    -0.28
    POSITIVE LOGITS
    dale
    0.21
    ed
    0.20
    y
    0.19
    a
    0.18
    ing
    0.18
    d
    0.18
    rq
    0.18
    ourcing
    0.17
    chaft
    0.17
    chrift
    0.17
    Act Density 0.182%

    No Known Activations