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

    Neuronpedia

    INDEX
    Explanations

    starting and ending phrases in texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ftu
    -0.87
     fta
    -0.86
     »>
    -0.85
     thut
    -0.83
    :,,
    -0.83
    «<
    -0.80
     fince
    -0.79
     fte
    -0.79
     ftre
    -0.79
     Abbé
    -0.77
    POSITIVE LOGITS
     currently
    0.92
     immediate
    0.91
     presently
    0.86
     current
    0.83
    current
    0.75
     today
    0.73
     interim
    0.73
     Currently
    0.72
    Currently
    0.72
    immediate
    0.72
    Act Density 0.345%

    No Known Activations