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

    Neuronpedia

    INDEX
    Explanations

    mentions of organizations and advocacy groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghan
    -0.17
    queda
    -0.16
    ìĭ¸
    -0.15
    eck
    -0.15
    arkan
    -0.15
     confession
    -0.15
     confess
    -0.15
    arendra
    -0.14
     ìĿ¸ìłķ
    -0.14
    ãĥĥãĤ«ãĥ¼
    -0.14
    POSITIVE LOGITS
     demanded
    0.26
     demand
    0.26
    demand
    0.25
     demands
    0.25
     Demand
    0.25
     demanding
    0.24
     filed
    0.23
    lod
    0.23
    Demand
    0.21
     lodge
    0.21
    Act Density 0.172%

    No Known Activations