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

    Neuronpedia

    INDEX
    Explanations

    references to historical political and economic power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vermelhas
    -0.50
    guin
    -0.49
     rojas
    -0.48
     rosse
    -0.47
    trui
    -0.42
     esponja
    -0.42
    ριν
    -0.41
    ()['
    -0.40
    bula
    -0.40
     fermo
    -0.40
    POSITIVE LOGITS
    Hentet
    0.74
    RegressionTest
    0.73
    ReusableCell
    0.71
    WriteBarrier
    0.66
    脚注の使い方
    0.65
    0.62
     agenda
    0.60
     للمعارف
    0.59
    UnusedPrivate
    0.59
    ędzy
    0.58
    Act Density 0.423%

    No Known Activations