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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in positions of authority or leadership, particularly with the word "then" indicating past roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anches
    -0.18
    ungs
    -0.16
    lice
    -0.14
    CKER
    -0.14
    .peer
    -0.14
    annel
    -0.14
    167
    -0.14
    ìľ¡
    -0.14
    omi
    -0.13
    иÑģк
    -0.13
    POSITIVE LOGITS
    pak
    0.15
    *sp
    0.15
    abouts
    0.14
    astr
    0.14
    eto
    0.14
    -et
    0.14
    ÄĻp
    0.14
    imest
    0.13
    EGA
    0.13
    odka
    0.13
    Act Density 0.027%

    No Known Activations