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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellido
    -0.56
    arithmic
    -0.56
    مصادر
    -0.55
    хьтан
    -0.55
     autorytatywna
    -0.54
     disambiguazione
    -0.54
    andte
    -0.53
    UnitTesting
    -0.53
    OutputType
    -0.53
     realize
    -0.52
    POSITIVE LOGITS
     Yeah
    1.94
    Yeah
    1.83
     Okay
    1.78
    Okay
    1.71
    Hmm
    1.65
     Hmm
    1.62
    Huh
    1.59
     Yes
    1.54
    Yep
    1.54
     Yep
    1.47
    Act Density 0.081%

    No Known Activations