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

    Neuronpedia

    INDEX
    Explanations

    words related to plural nouns and their suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sWith
    -0.34
    ski
    -0.31
    tw
    -0.27
    ships
    -0.27
    sk
    -0.26
    sq
    -0.26
    site
    -0.26
    sch
    -0.25
    sheet
    -0.25
    the
    -0.24
    POSITIVE LOGITS
    oftware
    0.37
    earch
    0.35
    se
    0.35
    cence
    0.33
    cent
    0.32
    pread
    0.32
    mith
    0.31
    aurus
    0.31
    que
    0.30
    presso
    0.30
    Act Density 0.067%

    No Known Activations