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

    Neuronpedia

    INDEX
    Explanations

    references to historical oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iras
    -0.17
    ibal
    -0.14
    opoulos
    -0.14
     («
    -0.14
    _('
    -0.14
    .rt
    -0.14
    rava
    -0.14
    otec
    -0.13
    otts
    -0.13
    .matcher
    -0.13
    POSITIVE LOGITS
     Party
    0.16
    enser
    0.15
    ControlItem
    0.15
     BÄĽ
    0.14
    .party
    0.14
     Dept
    0.14
     QQ
    0.14
    Dept
    0.14
     township
    0.14
    kiye
    0.14
    Act Density 0.000%

    No Known Activations