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

    Neuronpedia

    INDEX
    Explanations

    patterns of dashes used for emphasis or separation of phrases

    oai_token-act-pair · gpt-3.5-turbo

    patterns that involve numerical or statistical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tumblr
    -0.56
    rote
    -0.54
    940
    -0.53
     OC
    -0.52
     Submit
    -0.51
     770
    -0.51
    776
    -0.51
     Revised
    -0.51
    MSN
    -0.51
     UCHIJ
    -0.51
    POSITIVE LOGITS
    of
    1.27
    OF
    0.88
    Of
    0.88
     thereof
    0.80
    luster
    0.70
     of
    0.69
     Of
    0.67
    oft
    0.66
     Lauder
    0.66
    rift
    0.65
    Act Density 0.796%

    No Known Activations