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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causality or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.91
     étoient
    -0.82
     avoient
    -0.79
     مشين
    -0.76
     intptr
    -0.74
     Италијани
    -0.74
     secondaires
    -0.69
    
    -0.68
     fevere
    -0.68
     الحره
    -0.68
    POSITIVE LOGITS
     thereby
    0.81
     hopes
    0.72
     valor
    0.71
     thoroughly
    0.62
     closely
    0.60
    flüs
    0.56
    phazard
    0.55
    valor
    0.55
    bital
    0.55
    ënt
    0.54
    Act Density 0.067%

    No Known Activations