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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "reflect" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ejus
    -0.77
     оригіналу
    -0.76
     Normdatei
    -0.73
    sizeCache
    -0.72
     يتيمه
    -0.71
     brancas
    -0.71
    covariance
    -0.70
    mathsf
    -0.69
     coisa
    -0.69
    Personendaten
    -0.69
    POSITIVE LOGITS
     reflected
    2.03
     reflecting
    2.02
     reflection
    1.96
     reflect
    1.95
     reflections
    1.94
     reflects
    1.94
     Reflect
    1.88
    reflect
    1.84
     refle
    1.77
     Reflection
    1.72
    Act Density 0.041%

    No Known Activations