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

    Neuronpedia

    INDEX
    Explanations

    references to the White House and its associated entities or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .RightToLeft
    -0.14
    scopes
    -0.14
    ahun
    -0.13
    adla
    -0.13
    .BorderFactory
    -0.13
    hra
    -0.13
    _peer
    -0.13
    ÃĸL
    -0.13
    _associ
    -0.13
    .City
    -0.13
    POSITIVE LOGITS
    gov
    0.20
    .gov
    0.19
    undry
    0.17
    太éĥİ
    0.16
    .nih
    0.16
    inator
    0.15
    vil
    0.15
    èĹ
    0.14
    ASE
    0.14
     White
    0.14
    Act Density 0.060%

    No Known Activations