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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate conflict or controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imony
    -0.16
    reau
    -0.15
    nier
    -0.15
    enance
    -0.14
    ern
    -0.14
     impuls
    -0.14
    bai
    -0.14
    agua
    -0.14
    mony
    -0.14
     succ
    -0.14
    POSITIVE LOGITS
     dormant
    0.28
     reaction
    0.23
     responses
    0.23
     debate
    0.23
     response
    0.23
     reactions
    0.22
    -response
    0.19
    åıįåºĶ
    0.19
     Dorm
    0.18
     latent
    0.18
    Act Density 0.098%

    No Known Activations