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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reconc
    -0.73
     vit
    -0.69
    unal
    -0.69
     intangible
    -0.62
     plac
    -0.61
    ortium
    -0.60
     unpre
    -0.60
    Lex
    -0.59
     prosperous
    -0.58
    ained
    -0.58
    POSITIVE LOGITS
    burg
    1.03
    wald
    0.86
    seys
    0.82
    hao
    0.80
    walker
    0.80
    walking
    0.79
    brook
    0.78
    acre
    0.77
    wood
    0.75
    rigan
    0.75
    Act Density 0.036%

    No Known Activations