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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the source of information or identity, specifically words related to graduation or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikel
    -0.15
    gnore
    -0.15
    ushman
    -0.14
    acy
    -0.14
    neas
    -0.14
     Sa
    -0.14
    ิร
    -0.14
     Thornton
    -0.14
    aina
    -0.14
    oins
    -0.14
    POSITIVE LOGITS
    kie
    0.17
    мени
    0.17
    :animated
    0.16
    éĺ³åŁİ
    0.15
    TRA
    0.15
     Haupt
    0.14
    åIJĪ
    0.14
    enet
    0.14
    ırı
    0.14
    inee
    0.14
    Act Density 0.005%

    No Known Activations