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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "stop."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mob
    -0.15
    ãģĿãĤĮãģ¯
    -0.14
     Ramos
    -0.14
    ãĥ¬ãĥ³
    -0.14
     Aw
    -0.14
    ALAR
    -0.14
     mob
    -0.14
     вÑģ
    -0.13
    aws
    -0.13
    ERO
    -0.13
    POSITIVE LOGITS
    uat
    0.15
    arter
    0.15
    ksam
    0.14
    ạch
    0.14
    arters
    0.14
     Cham
    0.14
    ảng
    0.14
    å¾
    0.14
    ialis
    0.13
    TypeInfo
    0.13
    Act Density 0.005%

    No Known Activations