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

    Neuronpedia

    INDEX
    Explanations

    references to cities, particularly Kuala Lumpur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Philippine
    -0.16
    pron
    -0.16
     Indonesian
    -0.15
    nesia
    -0.15
    _ma
    -0.15
     kariy
    -0.15
     Indonesia
    -0.14
     Indones
    -0.14
    Abb
    -0.14
    arness
    -0.14
    POSITIVE LOGITS
     Perl
    0.19
     Johan
    0.17
     laut
    0.16
    antan
    0.16
     impulse
    0.15
     Bes
    0.15
    raman
    0.15
     Palestin
    0.14
     Hulu
    0.14
    ãĤ²
    0.14
    Act Density 0.056%

    No Known Activations