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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "can" indicating capability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itzer
    -0.17
    ersist
    -0.16
    verts
    -0.15
     Mits
    -0.15
    iesen
    -0.15
    ahren
    -0.15
    GNUC
    -0.15
    etler
    -0.14
    utz
    -0.14
    lettes
    -0.14
    POSITIVE LOGITS
     tell
    0.21
     promise
    0.19
     see
    0.19
     hear
    0.18
     picture
    0.18
     guarantee
    0.18
     sense
    0.17
     assurance
    0.17
     relate
    0.17
     smell
    0.17
    Act Density 0.049%

    No Known Activations