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

    Neuronpedia

    INDEX
    Explanations

    discussions related to historical injustices and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    หน่อย
    -0.68
    有点
    -0.60
    __*/
    -0.59
     Parece
    -0.58
     hoping
    -0.57
    Kinda
    -0.56
     kics
    -0.56
    simpleType
    -0.56
     biraz
    -0.55
    colgroup
    -0.55
    POSITIVE LOGITS
     przecież
    0.79
    又不是
    0.76
     objectively
    0.66
     clearly
    0.65
     unquestionably
    0.64
     demonstra
    0.63
     jamás
    0.61
     certainly
    0.61
    少なくとも
    0.61
     manifestly
    0.61
    Act Density 0.767%

    No Known Activations