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

    Neuronpedia

    INDEX
    Explanations

    descriptors and phrases indicating high levels or significant increases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gii
    -0.16
    Ÿ
    -0.15
    -Line
    -0.13
    propertyName
    -0.13
    æk
    -0.13
    _MAXIMUM
    -0.13
     Rooney
    -0.13
    Latch
    -0.13
    ï¼²
    -0.13
    ffen
    -0.13
    POSITIVE LOGITS
     pace
    0.22
     scale
    0.18
     clip
    0.18
     frequency
    0.17
    oser
    0.17
    clip
    0.16
     fashion
    0.16
     Fashion
    0.16
    325
    0.16
    316
    0.16
    Act Density 0.117%

    No Known Activations