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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to statistical models and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.35
     baratas
    -0.31
     budeme
    -0.30
     Theorie
    -0.30
    équation
    -0.28
     niego
    -0.28
     poissons
    -0.27
     demostrar
    -0.26
     Berechnung
    -0.26
    THEOREM
    -0.26
    POSITIVE LOGITS
     Weiſe
    1.00
     pleaſure
    1.00
    <unused68>
    0.97
    <unused23>
    0.97
    <unused41>
    0.97
    <unused8>
    0.97
    <unused74>
    0.97
     queſto
    0.97
    <unused42>
    0.97
    <pad>
    0.96
    Act Density 5.051%

    No Known Activations