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

    Neuronpedia

    INDEX
    Explanations

    repeated characters or symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -1.02
    .
    -0.93
     in
    -0.89
    ?
    -0.83
     
    -0.81
     is
    -0.78
     and
    -0.77
     a
    -0.76
     to
    -0.75
    :
    -0.73
    POSITIVE LOGITS
     myſelf
    1.17
    Autoritní
    1.13
     Jefus
    1.12
     itſelf
    1.08
     Theſe
    1.07
     Shakspeare
    1.06
    AsUp
    1.06
     Monfieur
    1.04
    RegressionTest
    1.02
    IndentedString
    1.01
    Act Density 0.528%

    No Known Activations