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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and controversies such as criticisms, debates, and protests

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTS
    -0.81
    UTF
    -0.69
    ¯
    -0.67
    utf
    -0.62
    acters
    -0.62
    ELF
    -0.60
    ï¸ı
    -0.60
    cpp
    -0.59
    Gray
    -0.59
     âī¡
    -0.58
    POSITIVE LOGITS
     hiatus
    0.97
    stage
    0.91
     sale
    0.87
     stage
    0.84
    shore
    0.82
    boarding
    0.81
     board
    0.79
    ibaba
    0.79
     patrol
    0.78
     autop
    0.78
    Act Density 0.027%

    No Known Activations