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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or structures in data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.64
    <eos>
    -0.52
     N
    -0.50
    <b>
    -0.47
    <code>
    -0.44
     "
    -0.44
     M
    -0.43
     I
    -0.43
    BeginContext
    -0.43
     “
    -0.43
    POSITIVE LOGITS
     itſelf
    0.98
     themſelves
    0.97
     myſelf
    0.96
     Majefty
    0.90
     uſed
    0.89
     Efq
    0.88
     himſelf
    0.86
     poffible
    0.86
     raiſ
    0.84
     Monfieur
    0.82
    Act Density 0.006%

    No Known Activations