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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to disagreements or disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usk
    -0.16
    mut
    -0.15
    mel
    -0.15
    绾
    -0.15
    irst
    -0.15
    erness
    -0.14
    pent
    -0.14
    621
    -0.14
    .sul
    -0.14
    à¸Ļาม
    -0.14
    POSITIVE LOGITS
    /question
    0.19
    /conf
    0.18
    ariat
    0.18
    ãĥ¥
    0.18
    reesome
    0.17
    ably
    0.15
    /problem
    0.15
    hle
    0.15
    isha
    0.14
    allback
    0.14
    Act Density 0.026%

    No Known Activations