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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an effort or journey towards achieving a specific goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an ability or effort to reach a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     omin
    -0.66
     doubtless
    -0.62
    Released
    -0.61
     debuted
    -0.60
     alluded
    -0.59
     hinted
    -0.59
     fortunately
    -0.58
     sprinkled
    -0.58
     evidently
    -0.58
     retrieved
    -0.57
    POSITIVE LOGITS
     oneself
    0.90
     Yourself
    0.76
    agon
    0.72
    ordinate
    0.71
    =-=-=-=-=-=-=-=-
    0.68
     anything
    0.66
     ç¥ŀ
    0.64
     any
    0.63
    WARD
    0.62
    your
    0.62
    Act Density 0.608%

    No Known Activations