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

    Neuronpedia

    INDEX
    Explanations

    verbs related to accomplishment or ability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capability or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĪ
    -0.70
    æľ
    -0.70
     wont
    -0.68
    æ©Ł
    -0.66
    é¾į
    -0.65
    Missing
    -0.61
    UC
    -0.61
     Archdemon
    -0.59
    ouring
    -0.58
    usra
    -0.58
    POSITIVE LOGITS
     freely
    0.88
     safely
    0.86
     comfortably
    0.85
     uninterrupted
    0.74
     lawfully
    0.74
     unlimited
    0.73
     efficiently
    0.73
    successfully
    0.72
     oneself
    0.72
     easily
    0.70
    Act Density 0.314%

    No Known Activations