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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight superlative or unique qualities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.87
    ✨:
    -0.68
    fjspx
    -0.68
     autorytatywna
    -0.67
     /\.(
    -0.67
    BuilderFactory
    -0.67
    XmlAccessType
    -0.63
    +#+#
    -0.63
     Baillar
    -0.63
    weile
    -0.63
    POSITIVE LOGITS
    はじめに
    0.56
    ::~
    0.55
    disambiguation
    0.55
    RuleContext
    0.54
    edema
    0.53
    $.
    0.51
    깥
    0.51
    UrlResolution
    0.50
    styleType
    0.49
     Roman
    0.48
    Act Density 0.012%

    No Known Activations