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

    Neuronpedia

    INDEX
    Explanations

    mentions of political structures and roles within a government context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruk
    -0.17
    pez
    -0.16
    lage
    -0.15
    veÅĻej
    -0.14
    898
    -0.14
     cé
    -0.14
    overflow
    -0.14
    oward
    -0.14
    kel
    -0.14
    (WIN
    -0.14
    POSITIVE LOGITS
     Rafael
    0.16
     Mach
    0.16
    maps
    0.15
     Prote
    0.15
    ariant
    0.14
     Pri
    0.14
    seys
    0.14
     Bam
    0.14
    Compat
    0.14
    205
    0.14
    Act Density 0.086%

    No Known Activations