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

    Neuronpedia

    INDEX
    Explanations

    numeric values and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPATH
    -0.70
    참고
    -0.68
    ,:);
    -0.66
    ukone
    -0.65
    thâu
    -0.64
    Personensuche
    -0.64
    itinéraire
    -0.64
     للمعارف
    -0.63
    ledem
    -0.62
    Brie
    -0.61
    POSITIVE LOGITS
    5
    1.08
    0
    1.07
    4
    0.99
    6
    0.97
    3
    0.96
    2
    0.93
    7
    0.88
    8
    0.87
    9
    0.86
    1
    0.84
    Act Density 1.963%

    No Known Activations