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

    Neuronpedia

    INDEX
    Explanations

    terms related to color shading and tones

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Alexis
    -0.73
     Ellis
    -0.69
     perut
    -0.68
    (()
    -0.65
    ={({
    -0.65
    ähig
    -0.65
    riki
    -0.64
    Alexis
    -0.63
     nhat
    -0.62
     Burgos
    -0.61
    POSITIVE LOGITS
    Shade
    1.60
     Shades
    1.60
     Shade
    1.59
    shade
    1.58
    Shades
    1.46
    shades
    1.44
     shade
    1.43
     shades
    1.42
     shading
    1.35
    shaded
    1.22
    Act Density 0.006%

    No Known Activations