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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications or formal citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     port
    -0.17
    prung
    -0.16
     Kemp
    -0.15
     Cutter
    -0.15
     mars
    -0.15
    òn
    -0.15
     meaning
    -0.14
     |
    -0.14
     cuts
    -0.14
     post
    -0.14
    POSITIVE LOGITS
     ----------------------------------------------------------------------------↵
    0.15
    rollo
    0.15
    ectl
    0.15
     ============================================================================↵
    0.15
    raphics
    0.14
    yb
    0.14
    itesse
    0.14
    ERENCE
    0.14
    -être
    0.14
    roti
    0.14
    Act Density 0.094%

    No Known Activations