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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    2
    -0.63
    5
    -0.57
    1
    -0.56
    3
    -0.53
    7
    -0.51
    сте
    -0.51
    I
    -0.50
    in
    -0.49
    tilde
    -0.49
    ine
    -0.49
    POSITIVE LOGITS
     、
    1.47
    、
    1.25
    )、
    1.24
    DockStyle
    1.22
    ,-,
    1.20
    LookAnd
    1.14
    ﹑
    1.14
    .$,
    1.11
    ,...,
    1.09
    StructEnd
    1.07
    Act Density 0.175%

    No Known Activations