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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that indicate relationships or connections between variables or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.72
    Aims
    -0.64
    AxisAlignment
    -0.58
     StatelessWidget
    -0.56
    prefixer
    -0.50
    hdashline
    -0.49
    restler
    -0.48
    CodeAnalysis
    -0.48
    ссора
    -0.48
    HasAnnotation
    -0.48
    POSITIVE LOGITS
     corresponding
    1.13
    相应
    0.94
     respective
    0.93
    corresponding
    0.93
     Corresponding
    0.92
    OGND
    0.88
     counterpart
    0.87
     entsprechende
    0.86
     counterparts
    0.85
    Corresponding
    0.84
    Act Density 0.366%

    No Known Activations