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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to truth, investigations, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akk
    -0.19
    quot
    -0.16
    ãģĵãģĨ
    -0.15
    çĤī
    -0.14
    untime
    -0.14
    Exc
    -0.14
    ãģ¡ãĤĥãĤĵ
    -0.14
    itu
    -0.14
     æľĿ
    -0.14
    زر
    -0.13
    POSITIVE LOGITS
    indsight
    0.18
    ostel
    0.15
    verting
    0.15
    ozo
    0.15
    ocab
    0.14
    TT
    0.14
    odom
    0.14
    -door
    0.14
     minim
    0.14
    osten
    0.14
    Act Density 0.074%

    No Known Activations