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

    Neuronpedia

    INDEX
    Explanations

    identifiers and programming constructs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.49
    (
    -0.47
     
    -0.47
    -
    -0.46
     and
    -0.46
    _
    -0.46
    /
    -0.42
    ・
    -0.42
     &
    -0.40
     [
    -0.39
    POSITIVE LOGITS
    <unused41>
    1.14
    <unused23>
    1.14
    <unused14>
    1.14
    <unused17>
    1.14
    [@BOS@]
    1.14
    <pad>
    1.14
    <unused3>
    1.14
    <unused8>
    1.14
    <unused42>
    1.14
    <unused51>
    1.14
    Act Density 0.022%

    No Known Activations