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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks signaling the end of statements or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Amicalement
    -1.13
     '\\;'
    -1.10
     GenerationType
    -1.08
    tagHelperRunner
    -0.97
    NUMX
    -0.95
     <=",
    -0.92
    IntoConstraints
    -0.92
    >\<^
    -0.88
    ^(@)
    -0.87
    AndEndTag
    -0.86
    POSITIVE LOGITS
    ↵
    0.88
    ↵↵
    0.82
    <eos>
    0.81
    ↵↵↵
    0.81
    ↵↵↵↵
    0.81
    is
    0.77
    http
    0.73
                                   
    0.73
    K
    0.72
    https
    0.70
    Act Density 0.421%

    No Known Activations