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

    Neuronpedia

    INDEX
    Explanations

    references to "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atrix
    -0.18
    berra
    -0.17
    coni
    -0.16
    atures
    -0.16
    aden
    -0.16
    holes
    -0.16
    prs
    -0.16
    oot
    -0.15
    rowse
    -0.15
    ultimate
    -0.15
    POSITIVE LOGITS
    wards
    0.20
    ted
    0.20
    land
    0.20
    sert
    0.19
    ta
    0.19
    ting
    0.18
    -of
    0.17
     khá»ıi
    0.17
    ters
    0.17
    tesy
    0.17
    Act Density 0.214%

    No Known Activations