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

    Neuronpedia

    INDEX
    Explanations

    references to citizens and citizen engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.18
    gg
    -0.17
    edException
    -0.17
    loon
    -0.17
    oul
    -0.16
    amera
    -0.16
    Ù
    -0.15
    erras
    -0.15
    gin
    -0.15
    svn
    -0.15
    POSITIVE LOGITS
    ry
    0.31
    hood
    0.21
    RY
    0.18
    stvo
    0.17
    rics
    0.17
    /res
    0.17
    SHIP
    0.17
    enge
    0.16
    RIES
    0.16
    ries
    0.16
    Act Density 0.013%

    No Known Activations