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

    Neuronpedia

    INDEX
    Explanations

    specific programming language-related keywords or function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themſelves
    -0.88
     iſt
    -0.84
     eſſ
    -0.80
     tranſ
    -0.80
     Anſ
    -0.79
     ſeveral
    -0.78
     paſſ
    -0.77
     Theſe
    -0.76
     Eſ
    -0.75
     neceſſ
    -0.75
    POSITIVE LOGITS
     m
    2.66
    m
    2.31
     M
    1.74
    M
    1.49
     м
    1.44
     getM
    1.28
    getM
    1.27
    ｍ
    1.25
    mR
    1.17
     م
    1.14
    Act Density 0.152%

    No Known Activations