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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and formatting tags in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pez
    -0.45
     sab
    -0.42
    子
    -0.39
    resz
    -0.39
     kue
    -0.38
    子を
    -0.37
    శ
    -0.37
     zum
    -0.37
    ιν
    -0.37
     trampa
    -0.36
    POSITIVE LOGITS
     ―――――
    1.02
     raiſ
    1.02
    ſelf
    1.02
     Chwiliwch
    0.98
     itſelf
    0.95
     resourceCulture
    0.92
     Majefty
    0.91
     myſelf
    0.89
    ]--;
    0.88
     uſed
    0.88
    Act Density 0.466%

    No Known Activations