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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize conjunctions or linking ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    請繼續往下閱讀
    -0.47
     Corea
    -0.45
    Filmografie
    -0.45
     Carls
    -0.44
    RuleContext
    -0.43
    legungen
    -0.43
    xmlns
    -0.42
     Perla
    -0.42
    Hochspringen
    -0.42
    Kite
    -0.41
    POSITIVE LOGITS
    findpost
    0.78
    And
    0.68
     And
    0.68
     certainly
    0.67
    تقاوى
    0.66
     dessutom
    0.63
    而且
    0.63
     memang
    0.63
     although
    0.62
    ostante
    0.62
    Act Density 0.282%

    No Known Activations