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

    Neuronpedia

    INDEX
    Explanations

    references to nationality and identity within a contextual framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SizePolicy
    -0.14
    TextWriter
    -0.13
    _UNLOCK
    -0.12
    elize
    -0.12
     Sesso
    -0.12
     Writers
    -0.12
    irsch
    -0.11
    ilden
    -0.11
    577
    -0.11
    Äĥm
    -0.11
    POSITIVE LOGITS
     work
    1.09
     working
    0.96
     works
    0.91
     worked
    0.90
    å·¥ä½ľ
    0.89
     WORK
    0.88
    work
    0.87
    -work
    0.86
    .work
    0.84
    working
    0.84
    Act Density 0.914%

    No Known Activations