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

    Neuronpedia

    INDEX
    Explanations

    references to previous works or adaptations in a broader context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arten
    -0.18
    ncy
    -0.16
    ugh
    -0.15
    creen
    -0.15
    rt
    -0.15
    ripper
    -0.15
    autiful
    -0.15
    lom
    -0.14
    ascus
    -0.14
    pta
    -0.14
    POSITIVE LOGITS
     seu
    0.18
     nosso
    0.17
     mesmo
    0.16
     same
    0.16
    λά
    0.16
     veto
    0.15
     próp
    0.15
    inear
    0.15
     mismo
    0.14
     lado
    0.14
    Act Density 0.012%

    No Known Activations