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

    Neuronpedia

    INDEX
    Explanations

    instances of hypocrisy or contradictions in behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.71
     Winaray
    -0.65
     censiti
    -0.56
     '\\;'
    -0.56
    FromNib
    -0.54
     يتيمه
    -0.54
    الإنجليزية
    -0.54
     للمعارف
    -0.51
     Numerade
    -0.50
    principalTable
    -0.50
    POSITIVE LOGITS
     parents
    0.42
     parent
    0.41
     hijo
    0.40
     parental
    0.40
     family
    0.38
     çocu
    0.37
     familia
    0.36
     son
    0.35
     Eltern
    0.35
    parents
    0.34
    Act Density 0.446%

    No Known Activations