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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibraries
    -0.16
    ashire
    -0.15
    зв
    -0.14
    izzy
    -0.14
    typed
    -0.14
    ijkstra
    -0.14
    unar
    -0.14
    igers
    -0.14
    minster
    -0.13
    Argb
    -0.13
    POSITIVE LOGITS
    uter
    0.16
    pery
    0.15
    ender
    0.14
    int
    0.14
    -elect
    0.14
    izo
    0.14
    ateg
    0.14
    çľ
    0.14
    opoulos
    0.14
    ex
    0.13
    Act Density 0.149%

    No Known Activations