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

    Neuronpedia

    INDEX
    Explanations

    language related to conflict and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aes
    -0.15
    离
    -0.14
    ÑĮÑİÑĤ
    -0.14
    ParameterValue
    -0.14
    hq
    -0.14
    Ģ
    -0.14
     ë©
    -0.14
    Ĭ¶
    -0.14
    ause
    -0.13
    .EventArgs
    -0.13
    POSITIVE LOGITS
    ät
    0.16
     Shields
    0.15
    ritch
    0.15
     sic
    0.14
    itr
    0.14
    ric
    0.14
     Wait
    0.14
    iz
    0.14
    ä¼
    0.14
     Spiel
    0.13
    Act Density 0.006%

    No Known Activations