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

    Neuronpedia

    INDEX
    Explanations

    language related to arguments, debates, and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виправивши
    -0.74
     cref
    -0.72
     FetchType
    -0.65
    ẵng
    -0.65
     徐
    -0.65
     بيها
    -0.61
     ComVisible
    -0.60
    ocities
    -0.59
    initializeApp
    -0.58
     Kron
    -0.58
    POSITIVE LOGITS
     argue
    1.81
     argues
    1.71
     arguing
    1.68
     argued
    1.66
     arguments
    1.52
     Arguments
    1.50
     argu
    1.34
    argue
    1.30
     debate
    1.30
    Arguments
    1.28
    Act Density 0.160%

    No Known Activations