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

    Neuronpedia

    INDEX
    Explanations

    clauses indicating exceptions or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sn
    -0.17
     sn
    -0.16
    omen
    -0.14
    aca
    -0.14
    138
    -0.14
    IN
    -0.14
    over
    -0.14
    Sn
    -0.14
     sounding
    -0.14
     Fra
    -0.14
    POSITIVE LOGITS
    outu
    0.17
     slightly
    0.15
    orsk
    0.15
    Oak
    0.15
    Orm
    0.15
    ãģĵãģ¡ãĤī
    0.15
    iв
    0.15
    maal
    0.14
     additionally
    0.14
    WISE
    0.14
    Act Density 0.151%

    No Known Activations