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

    Neuronpedia

    INDEX
    Explanations

    patterns of repeated phrases starting with "from"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.99
     myſelf
    -0.97
     Shakspeare
    -0.95
     Monfieur
    -0.94
     themſelves
    -0.91
     doubtnut
    -0.89
     himſelf
    -0.86
     iſt
    -0.85
     becauſe
    -0.82
     raiſ
    -0.81
    POSITIVE LOGITS
    from
    0.92
    __(/*!
    0.65
    scrapy
    0.58
    package
    0.55
    import
    0.53
    for
    0.51
     the
    0.51
     mais
    0.51
     Le
    0.50
     K
    0.50
    Act Density 0.038%

    No Known Activations