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

    Neuronpedia

    INDEX
    Explanations

    the frequency of the substring "ch" in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.78
     GenerationType
    -0.63
    KEA
    -0.61
     تضيفلها
    -0.61
     Económica
    -0.60
    ]();
    -0.60
     Wiktionnaire
    -0.59
    허
    -0.59
    vernment
    -0.58
    '''
    -0.58
    POSITIVE LOGITS
    ch
    3.32
    CH
    1.64
    chs
    1.11
    chman
    1.11
    chn
    1.03
    chl
    1.00
    chm
    0.98
    х
    0.97
     ch
    0.92
    chy
    0.90
    Act Density 0.095%

    No Known Activations