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

    Neuronpedia

    INDEX
    Explanations

    variables related to numerical values or constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.98
     myſelf
    -0.95
    ſelf
    -0.90
     compri
    -0.88
     Chriſt
    -0.87
     Lieben
    -0.85
     ſhall
    -0.84
     iſt
    -0.84
     ་་
    -0.84
     Schwe
    -0.83
    POSITIVE LOGITS
     K
    1.57
    K
    1.53
     k
    1.40
    k
    1.29
     nationaux
    0.98
    assium
    0.95
    𝐤
    0.92
    К
    0.91
     К
    0.90
     Nick
    0.88
    Act Density 0.139%

    No Known Activations