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

    Neuronpedia

    INDEX
    Explanations

    references to large data files and their complexities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.68
    iecie
    -0.54
     AssemblyVersion
    -0.53
    GIVEREF
    -0.52
    uurs
    -0.52
    UnitTesting
    -0.51
    bouts
    -0.50
    vallis
    -0.50
    尼斯
    -0.50
     تضيفلها
    -0.49
    POSITIVE LOGITS
     alphabetically
    0.65
    حياتها
    0.61
     deluge
    0.56
    حياته
    0.55
    OGND
    0.55
     avalanche
    0.51
     hundreds
    0.50
    hundreds
    0.50
    ırl
    0.48
     Tribut
    0.48
    Act Density 0.098%

    No Known Activations