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

    Neuronpedia

    INDEX
    Explanations

    words related to changes or dynamics in a situation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     toledo
    -0.91
     mlb
    -0.91
     stockholm
    -0.88
     secon
    -0.88
     beverly
    -0.88
     madonna
    -0.85
     erad
    -0.83
     getty
    -0.83
     reluct
    -0.81
     fto
    -0.80
    POSITIVE LOGITS
     nor
    0.73
    <bos>
    0.68
     whatsoever
    0.55
     underlying
    0.54
     oder
    0.54
     or
    0.53
     fundamentals
    0.53
     overall
    0.53
     resourceCulture
    0.51
    Cependant
    0.50
    Act Density 0.214%

    No Known Activations