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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to political intrigue and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    t
    -0.19
    i
    -0.17
    ÑĮ
    -0.15
    ksam
    -0.15
    ourt
    -0.15
    ainment
    -0.15
    tual
    -0.15
    Ùĩ
    -0.14
    682
    -0.14
    ordion
    -0.14
    POSITIVE LOGITS
    er
    0.18
    su
    0.16
    [email
    0.15
    âīł
    0.14
     Pavilion
    0.14
     à¹Ĩ
    0.14
    /Graphics
    0.14
    erland
    0.14
    ever
    0.13
    ev
    0.13
    Act Density 0.010%

    No Known Activations