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

    Neuronpedia

    INDEX
    Explanations

    references to core concepts or foundational elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ent
    -0.50
     Under
    -0.50
    Under
    -0.50
    QMetaType
    -0.49
    еры
    -0.48
    Hale
    -0.48
    Garth
    -0.48
     Gilbert
    -0.48
    ：「
    -0.48
    trc
    -0.47
    POSITIVE LOGITS
    underlying
    0.89
     underlying
    0.84
     Underlying
    0.83
     underlie
    0.78
     constituting
    0.73
    rrggbb
    0.73
    WebVitals
    0.72
     المعيارى
    0.71
     underlies
    0.71
    Underlying
    0.71
    Act Density 0.202%

    No Known Activations