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

    Neuronpedia

    INDEX
    Explanations

    ellipses or sequences of repeated punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.23
     Efq
    -1.22
     itſelf
    -1.22
     Monfieur
    -1.21
     becauſe
    -1.18
     themſelves
    -1.17
     myſelf
    -1.13
    ſelf
    -1.11
     Diſ
    -1.10
     Houſe
    -1.08
    POSITIVE LOGITS
     /
    0.50
     {,
    0.49
    <eos>
    0.48
     "(
    0.47
     ”
    0.46
     de
    0.44
     zero
    0.44
     Zero
    0.44
     {;
    0.44
     min
    0.43
    Act Density 0.493%

    No Known Activations