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

    Neuronpedia

    INDEX
    Explanations

    references to low severity issues or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ührt
    -0.43
    Headquarters
    -0.42
    Large
    -0.42
    AndGet
    -0.41
     kasarigan
    -0.41
     democrática
    -0.40
     democrá
    -0.40
    LARGE
    -0.40
     Large
    -0.40
    large
    -0.39
    POSITIVE LOGITS
     minor
    3.91
    Minor
    3.52
    minor
    3.50
     Minor
    3.50
     MINOR
    3.09
    MINOR
    2.84
     minors
    2.11
     minore
    1.80
     minori
    1.77
     mineures
    1.68
    Act Density 0.110%

    No Known Activations