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

    Neuronpedia

    INDEX
    Explanations

    phrases related to justification and rationale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.98
     betweenstory
    -0.97
    ItemBackground
    -0.93
     صوتيه
    -0.92
    AsUp
    -0.91
     فريبيس
    -0.91
     ujednoznacz
    -0.89
     NSCoder
    -0.87
    RegressionTest
    -0.86
     متعلقه
    -0.85
    POSITIVE LOGITS
     which
    0.72
     including
    0.70
     especially
    0.66
     whether
    0.60
     particularly
    0.58
     notamment
    0.58
     δη
    0.56
     perhaps
    0.55
     incluyendo
    0.54
     cioè
    0.52
    Act Density 0.388%

    No Known Activations