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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols in the text

    oai_token-act-pair · gpt-3.5-turbo

    the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     explan
    -0.93
     agre
    -0.90
    chnology
    -0.83
     ende
    -0.83
     behavi
    -0.82
    ngth
    -0.80
     obser
    -0.79
     horizont
    -0.76
     viability
    -0.75
     independ
    -0.75
    POSITIVE LOGITS
    é¾į
    0.93
    ef
    0.91
    ãĤ±
    0.87
    °
    0.82
    irect
    0.82
    ļ
    0.82
    º
    0.82
    Ĭ
    0.80
    ¤
    0.80
    Counter
    0.79
    Act Density 0.041%

    No Known Activations