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

    Neuronpedia

    INDEX
    Explanations

    patterns of character sequences that include the letter 'm'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themſelves
    -0.93
     ſeveral
    -0.83
     ſel
    -0.80
    wiſe
    -0.79
     Theſe
    -0.79
    ════════
    -0.78
     viſ
    -0.78
     myſelf
    -0.77
     eſſ
    -0.77
     Diſ
    -0.77
    POSITIVE LOGITS
     m
    2.02
    m
    1.46
     M
    1.45
    M
    1.10
    getM
    1.09
     м
    1.08
     getM
    0.99
     K
    0.94
     م
    0.94
     r
    0.93
    Act Density 0.128%

    No Known Activations