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

    Neuronpedia

    INDEX
    Explanations

    phrases related to groups of people, especially in contexts suggesting a degree of seriousness or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     préférence
    -0.56
    leby
    -0.53
     către
    -0.52
     partiellement
    -0.51
     ailleurs
    -0.50
     scurt
    -0.46
     ägg
    -0.46
     jednocześnie
    -0.45
     difficultés
    -0.44
     chrétiens
    -0.44
    POSITIVE LOGITS
     outta
    0.77
     damn
    0.73
     really
    0.73
     absolutely
    0.69
     REALLY
    0.68
    !
    0.64
    Absolutely
    0.62
    !',
    0.62
     fuckin
    0.62
     motherfucker
    0.61
    Act Density 0.207%

    No Known Activations