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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "como" or its variations, indicating comparisons or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     feroit
    -0.58
     étoient
    -0.56
    LookAnd
    -0.56
     Majefty
    -0.56
     Diſ
    -0.56
     Theſe
    -0.55
     étoit
    -0.55
     picioare
    -0.54
     avoient
    -0.54
     ſon
    -0.54
    POSITIVE LOGITS
     como
    1.98
     как
    1.84
     як
    1.79
     comme
    1.77
     jako
    1.61
     sebagai
    1.57
     kaip
    1.56
     COMO
    1.48
     như
    1.48
    como
    1.45
    Act Density 0.125%

    No Known Activations