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

    Neuronpedia

    INDEX
    Explanations

    concepts related to balance and moderation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.45
    SharedCtor
    -0.44
     ModelExpression
    -0.43
    tableFuture
    -0.39
    +:+
    -0.37
     actionMode
    -0.36
    enumii
    -0.34
    DeleteBehavior
    -0.34
    MenuInflater
    -0.34
    AxisSize
    -0.34
    POSITIVE LOGITS
     good
    3.77
    good
    3.27
    Good
    2.97
     GOOD
    2.91
     Good
    2.88
    GOOD
    2.73
     buena
    2.39
     buenas
    2.33
     gute
    2.30
     goede
    2.30
    Act Density 1.275%

    No Known Activations