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

    Neuronpedia

    INDEX
    Explanations

    specific numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.59
    岐
    -0.45
     absc
    -0.43
     nig
    -0.41
     pist
    -0.39
     twit
    -0.39
     Front
    -0.38
     divers
    -0.38
     Pound
    -0.38
     Supers
    -0.37
    POSITIVE LOGITS
     which
    0.73
     but
    0.69
     laikā
    0.65
     religione
    0.59
     although
    0.59
     and
    0.57
     including
    0.57
     whereas
    0.57
     albeit
    0.56
     allowing
    0.56
    Act Density 1.280%

    No Known Activations