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

    Neuronpedia

    INDEX
    Explanations

    terms related to software instructions and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ragaz
    -0.15
    zhou
    -0.15
    ecast
    -0.15
    uye
    -0.15
    etta
    -0.14
    hai
    -0.14
     Hai
    -0.14
     primero
    -0.14
     Toro
    -0.14
    bw
    -0.14
    POSITIVE LOGITS
    ôn
    0.21
    idade
    0.18
    agem
    0.17
    inha
    0.17
     itens
    0.17
     Brazilian
    0.16
     ê
    0.16
     tôn
    0.16
    inho
    0.16
     canh
    0.15
    Act Density 0.084%

    No Known Activations