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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and international affairs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     cryst
    -0.66
    APD
    -0.65
     oats
    -0.63
    TextColor
    -0.62
     Klux
    -0.61
     subtract
    -0.61
    natureconservancy
    -0.59
    Effective
    -0.59
    romising
    -0.58
    facebook
    -0.58
    POSITIVE LOGITS
    shi
    0.93
    icz
    0.91
    uala
    0.84
    ny
    0.83
    wu
    0.82
     Petersen
    0.81
    ewski
    0.80
    ius
    0.79
    oglu
    0.79
    quez
    0.79
    Act Density 0.122%

    No Known Activations