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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter combination "ch" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    зи
    -0.16
    Ïģαβ
    -0.15
    -Ta
    -0.15
    fab
    -0.14
    minor
    -0.14
    Å¡em
    -0.14
    coma
    -0.14
    chap
    -0.14
    ols
    -0.14
    archy
    -0.14
    POSITIVE LOGITS
     ch
    0.35
    [ch
    0.17
    oral
    0.17
    thon
    0.17
     Advance
    0.16
    ican
    0.16
    ExecutionContext
    0.15
    isel
    0.15
    atty
    0.15
    ills
    0.15
    Act Density 0.018%

    No Known Activations