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

    Neuronpedia

    INDEX
    Explanations

    the word "that" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Phry
    -0.68
     AppColors
    -0.60
     acorns
    -0.60
     $-.
    -0.59
    addContainerGap
    -0.57
     Nasty
    -0.57
     nakalista
    -0.57
     Prussian
    -0.57
     lekker
    -0.56
    berly
    -0.55
    POSITIVE LOGITS
     of
    0.73
    makeText
    0.72
     that
    0.61
     celui
    0.56
    TintMode
    0.56
     proveniente
    0.53
     belonging
    0.52
     derived
    0.52
    età
    0.52
    NullCheck
    0.51
    Act Density 0.046%

    No Known Activations