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

    Neuronpedia

    INDEX
    Explanations

    significant introductory phrases or concepts indicating importance or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    益
    -0.52
     descar
    -0.49
     menacing
    -0.48
     الشباب
    -0.44
     representing
    -0.44
     represented
    -0.44
     presentation
    -0.44
     regional
    -0.43
     grim
    -0.43
    gele
    -0.42
    POSITIVE LOGITS
     kisses
    0.88
     дописавши
    0.85
     loving
    0.79
    titleMargin
    0.79
    SharedCtor
    0.76
     kissed
    0.74
    __':
    0.74
    XmlAccessType
    0.73
    RTLD
    0.73
     kissing
    0.73
    Act Density 0.352%

    No Known Activations