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

    Neuronpedia

    INDEX
    Explanations

    specific names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Steen
    -0.71
     CWE
    -0.67
     Kennedy
    -0.67
     Axiom
    -0.65
    Axiom
    -0.65
    tyfik
    -0.65
    knię
    -0.65
     Dall
    -0.64
    八幡
    -0.64
     Mik
    -0.63
    POSITIVE LOGITS
    ſelf
    0.92
     Elsie
    0.90
     againſt
    0.86
    <?,
    0.83
    رير
    0.83
     Wolfsburg
    0.81
     Loth
    0.81
    этому
    0.80
     walnuts
    0.80
     Muay
    0.79
    Act Density 2.443%

    No Known Activations