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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific challenges or issues related to understanding or discussing complex subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osoph
    -0.15
    .sap
    -0.14
    ammad
    -0.13
    çuk
    -0.13
    udit
    -0.13
    .BLL
    -0.13
    enal
    -0.13
    -0.12
    iq
    -0.12
    enco
    -0.12
    POSITIVE LOGITS
    gnore
    0.16
     ëĭ¤ìļ´ë°Ľê¸°
    0.13
     nackte
    0.13
     ÃIJ
    0.13
    /stretch
    0.12
    /up
    0.12
    992
    0.12
    /fl
    0.12
     jadx
    0.12
    ACKET
    0.12
    Act Density 0.001%

    No Known Activations