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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to sharpness and clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.57
     Encyclopædia
    -0.55
    Grade
    -0.53
     jiwa
    -0.53
    AxisSize
    -0.53
     intensif
    -0.52
     Grade
    -0.52
     ſel
    -0.52
    atrième
    -0.52
     مشين
    -0.51
    POSITIVE LOGITS
     shining
    0.94
     shine
    0.89
     Shining
    0.87
     shines
    0.85
     shone
    0.82
    shining
    0.81
    sharp
    0.78
    Shine
    0.78
     Shine
    0.76
     فريبيس
    0.73
    Act Density 0.062%

    No Known Activations