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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving angle brackets, specifically related to inner products or expected values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rangle
    -0.67
     acque
    -0.61
     Kraus
    -0.60
    ास
    -0.57
     vader
    -0.56
     conmigo
    -0.56
     Potter
    -0.54
     Jacobson
    -0.54
     kasarigan
    -0.53
     Pal
    -0.53
    POSITIVE LOGITS
    langle
    2.04
    ⟨
    1.08
     〈
    1.03
    \{\\
    0.99
    〈
    0.93
    lceil
    0.89
     ce
    0.88
    Personendaten
    0.83
    OGND
    0.82
     Vario
    0.81
    Act Density 0.063%

    No Known Activations