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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military, government, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to joint organizations or committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utics
    -0.82
     Claus
    -0.76
    rx
    -0.68
     Constantin
    -0.66
    天
    -0.65
    doors
    -0.64
    begin
    -0.64
    FORE
    -0.63
    ages
    -0.62
     Cinderella
    -0.61
    POSITIVE LOGITS
     Joint
    0.84
    estinal
    0.83
    ness
    0.78
    ingly
    0.76
    oint
    0.74
     aid
    0.70
    iets
    0.70
     junction
    0.69
    TAIN
    0.69
     replacements
    0.66
    Act Density 0.009%

    No Known Activations