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

    Neuronpedia

    INDEX
    Explanations

    terms related to colors and visual characteristics in subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     astron
    -0.49
    StructEnd
    -0.45
    Cyfarwyddwr
    -0.44
     Савезне
    -0.43
    Itoa
    -0.42
     مرئيه
    -0.42
    ͯ
    -0.38
    outSlope
    -0.38
    Havolalar
    -0.38
     Sakit
    -0.37
    POSITIVE LOGITS
     brown
    1.05
     brownish
    1.00
     darker
    0.99
    brown
    0.93
     bronze
    0.89
     dark
    0.86
     Brown
    0.84
     darkening
    0.84
     bron
    0.84
    bronze
    0.83
    Act Density 0.310%

    No Known Activations