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

    Neuronpedia

    INDEX
    Explanations

    official mathematical notation and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.55
    SPATH
    -0.50
    knapp
    -0.50
    gania
    -0.47
     Hotspur
    -0.46
    pear
    -0.46
    fony
    -0.45
    radan
    -0.45
     """
    -0.45
    Abit
    -0.45
    POSITIVE LOGITS
    tså
    0.98
    0.96
     cioè
    0.94
     ovvero
    0.83
     Meaning
    0.83
    عنی
    0.82
    즉
    0.77
     means
    0.77
     meaning
    0.76
     protoimpl
    0.76
    Act Density 0.252%

    No Known Activations