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

    Neuronpedia

    INDEX
    Explanations

    statements and reactions related to public figures and their comments or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faveur
    -0.62
     supérieures
    -0.59
     extérieurs
    -0.56
     fekete
    -0.56
     spéciaux
    -0.56
     сожалению
    -0.55
    ņem
    -0.55
     jasa
    -0.54
    rão
    -0.54
     fehér
    -0.54
    POSITIVE LOGITS
     Dijo
    0.73
    出版年
    0.69
     commenting
    0.67
     saites
    0.66
     speaking
    0.66
     comments
    0.65
     interview
    0.65
    SequentialGroup
    0.65
     statements
    0.65
     talking
    0.65
    Act Density 0.331%

    No Known Activations