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

    Neuronpedia

    INDEX
    Explanations

    marked or emphasized text elements, particularly those signified by underscores or multiple underscore characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }));
    -0.65
    Hentet
    -0.62
    <>();
    -0.58
    <bos>
    -0.57
    }))
    -0.55
    }}}{\
    -0.54
    InjectAttribute
    -0.53
     tartalomajánló
    -0.52
    Chham
    -0.52
    ']")
    -0.51
    POSITIVE LOGITS
    TintMode
    0.60
    bukaan
    0.60
     moschino
    0.60
    MessageWindow
    0.60
     fotografico
    0.59
     inoxydable
    0.58
    orteur
    0.58
     titolata
    0.58
    ποτε
    0.57
     debout
    0.56
    Act Density 0.120%

    No Known Activations