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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĬ
    -0.20
    lack
    -0.16
    dag
    -0.14
    ãĤĪãģĨãģª
    -0.14
    ognito
    -0.14
    ãģĭãģij
    -0.14
    imu
    -0.14
    ichtig
    -0.13
    ذا
    -0.13
    996
    -0.13
    POSITIVE LOGITS
     sorts
    0.25
    course
    0.22
     course
    0.19
    /from
    0.19
    vido
    0.18
    -course
    0.16
    readcr
    0.16
    /by
    0.15
     lỼn
    0.15
    uger
    0.15
    Act Density 1.670%

    No Known Activations