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

    Neuronpedia

    INDEX
    Explanations

    variations of the phrase "I can" indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersist
    -0.19
    itzer
    -0.16
    iesen
    -0.15
    GNUC
    -0.14
    ãĥĥãĥģ
    -0.14
     Naturally
    -0.14
     ëĭ
    -0.14
    etler
    -0.14
    verts
    -0.14
    oshi
    -0.14
    POSITIVE LOGITS
     promise
    0.20
     v
    0.19
     guarantee
    0.18
     picture
    0.18
    Promise
    0.17
     see
    0.17
     tell
    0.17
     relate
    0.17
     smell
    0.16
     only
    0.16
    Act Density 0.048%

    No Known Activations