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

    Neuronpedia

    INDEX
    Explanations

    references to populism and related ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Forum
    -0.16
    次
    -0.15
    reuse
    -0.14
    bs
    -0.14
    ensburg
    -0.14
    unsupported
    -0.14
    egis
    -0.14
    ÄĽ
    -0.14
    è°ĭ
    -0.14
    ÅĻÃŃklad
    -0.14
    POSITIVE LOGITS
    Injector
    0.15
    571
    0.15
    axon
    0.14
     Punch
    0.14
     halls
    0.13
    .met
    0.13
    صÙĪÙĦ
    0.13
    ÑĥÑĢÑĥ
    0.13
     interfering
    0.13
    roperty
    0.13
    Act Density 0.003%

    No Known Activations