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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osorio
    -0.57
    ására
    -0.55
    csolódó
    -0.54
    ia
    -0.54
    いけない
    -0.54
     aikana
    -0.54
     numberOfRows
    -0.53
     Soriano
    -0.52
     själva
    -0.52
     prieš
    -0.52
    POSITIVE LOGITS
    t
    0.98
     t
    0.95
    T
    0.93
    getT
    0.81
    tt
    0.76
     T
    0.75
    ttt
    0.74
    ｔ
    0.72
    zt
    0.67
     tt
    0.66
    Act Density 0.075%

    No Known Activations