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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal issues and potential threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keterangan
    -0.17
    eland
    -0.16
    rika
    -0.15
    beck
    -0.15
    xde
    -0.15
     çİ
    -0.15
    ercul
    -0.15
     fare
    -0.14
    iec
    -0.14
    ewidth
    -0.14
    POSITIVE LOGITS
    idy
    0.18
    gage
    0.14
    aging
    0.14
    atha
    0.14
    avers
    0.14
    849
    0.14
    989
    0.14
     Cent
    0.14
    EXTERN
    0.13
    Mathf
    0.13
    Act Density 0.299%

    No Known Activations