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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical structures or notations involving sets and arrays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    The
    -0.35
    }}
    -0.31
    self
    -0.30
    !
    -0.30
     
    -0.30
    .
    -0.29
    1
    -0.29
    An
    -0.28
    (
    -0.27
    <code>
    -0.27
    POSITIVE LOGITS
     يتيمه
    1.03
    <unused14>
    0.98
    <unused43>
    0.98
    <unused74>
    0.98
    [@BOS@]
    0.98
    <unused8>
    0.97
    <unused51>
    0.97
    <unused41>
    0.97
    <unused28>
    0.97
    <unused17>
    0.97
    Act Density 0.051%

    No Known Activations