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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks signaling the end of statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.56
    ↵
    -0.55
    -
    -0.55
    I
    -0.54
    but
    -0.50
    (
    -0.50
    /
    -0.49
    tag
    -0.48
     I
    -0.47
    ிக
    -0.47
    POSITIVE LOGITS
    RegistryLite
    1.07
     CreateTagHelper
    1.05
     Efq
    1.02
     myſelf
    0.95
    ValueStyle
    0.95
    .")]
    0.92
     Wikimedijinoj
    0.89
    تقاوى
    0.88
    }`).
    0.88
    !")
    0.86
    Act Density 0.045%

    No Known Activations