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

    Neuronpedia

    INDEX
    Explanations

    terms associated with mathematical calculations and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.42
    AnimationsModule
    -0.40
    träger
    -0.40
    PerformLayout
    -0.39
    principalColumn
    -0.39
    XmlAccessorType
    -0.39
    н
    -0.38
    ン
    -0.38
     cherchés
    -0.38
    ria
    -0.37
    POSITIVE LOGITS
    mos
    0.71
    dan
    0.56
    da
    0.56
    day
    0.54
    re
    0.53
    das
    0.52
    dor
    0.52
    ment
    0.52
    ren
    0.50
    mente
    0.50
    Act Density 0.299%

    No Known Activations