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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removing or eliminating something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mpeg
    -0.66
    operation
    -0.61
    anwhile
    -0.60
     Maced
    -0.60
    Leaks
    -0.60
     Jonah
    -0.60
     Unch
    -0.58
    ORD
    -0.58
    ANS
    -0.56
     McDonnell
    -0.56
    POSITIVE LOGITS
    anium
    0.94
    ings
    0.83
    ged
    0.81
    icide
    0.80
    uations
    0.79
    icides
    0.79
    eness
    0.78
    uctions
    0.77
    ients
    0.75
    uation
    0.75
    Act Density 0.075%

    No Known Activations