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

    Neuronpedia

    INDEX
    Explanations

    numerical representations, specifically sequences of digits and their attributes in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     насељу
    -0.62
    }\]
    -0.55
     geldig
    -0.54
     calendriers
    -0.52
    Espèce
    -0.51
    서는
    -0.50
     culminated
    -0.49
    Autoritní
    -0.49
    }:=\
    -0.48
    {})
    -0.48
    POSITIVE LOGITS
    8
    0.70
    7
    0.70
    9
    0.70
    5
    0.70
    6
    0.69
    4
    0.65
    3
    0.64
    0
    0.58
     '\\;'
    0.57
    2
    0.56
    Act Density 1.204%

    No Known Activations