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

    Neuronpedia

    INDEX
    Explanations

    character sequences representing special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the empty token or the end of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.90
    chnology
    -0.86
     explan
    -0.83
     incorpor
    -0.81
    ngth
    -0.81
     behavi
    -0.78
     horizont
    -0.77
     manif
    -0.76
     ende
    -0.76
     thous
    -0.76
    POSITIVE LOGITS
    é¾į
    0.93
    °
    0.82
    º
    0.82
    ļ
    0.82
    ef
    0.82
    Fish
    0.80
    RAM
    0.80
    ãĥŃ
    0.79
    OUT
    0.77
    irect
    0.76
    Act Density 0.027%

    No Known Activations