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

    Neuronpedia

    INDEX
    Explanations

    centers and central themes in descriptions or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enheim
    -0.17
    omu
    -0.16
    ARGIN
    -0.15
     appDelegate
    -0.14
    dar
    -0.14
    weis
    -0.14
    sci
    -0.14
    lore
    -0.14
    ams
    -0.13
    anz
    -0.13
    POSITIVE LOGITS
    line
    0.20
    most
    0.19
    pieces
    0.18
    央
    0.17
    -center
    0.17
    /top
    0.17
     gravity
    0.17
    -central
    0.16
    OfFile
    0.16
    izers
    0.16
    Act Density 0.041%

    No Known Activations