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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused43>
    -1.11
    <unused41>
    -1.11
    <unused23>
    -1.10
    <unused74>
    -1.10
    <unused14>
    -1.10
    <unused8>
    -1.10
    <unused16>
    -1.09
    <unused28>
    -1.09
    <unused3>
    -1.09
    [@BOS@]
    -1.09
    POSITIVE LOGITS
    https
    0.94
    http
    0.89
     ...
    0.82
    Read
    0.76
    <eos>
    0.74
    ...
    0.73
    This
    0.69
     https
    0.69
    The
    0.69
     …
    0.66
    Act Density 0.683%

    No Known Activations