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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasized text or terminology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     "/")
    -0.64
     "];
    -0.57
     source
    -0.57
    ]_{\
    -0.57
    ""}
    -0.57
     '`
    -0.55
    {}",
    -0.54
     "\""
    -0.52
    }:${
    -0.51
     Sho
    -0.50
    POSITIVE LOGITS
    Personensuche
    0.88
    oredCriteria
    0.83
    UserScript
    0.82
    invokeLater
    0.78
    MessageTagHelper
    0.77
    lève
    0.71
    ScopeManager
    0.69
     Infórmanos
    0.69
    emphasis
    0.69
    InjectAttribute
    0.68
    Act Density 0.002%

    No Known Activations