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

    Neuronpedia

    INDEX
    Explanations

    descriptive words and phrases surrounding problems and solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows certain common words

    np_acts-logits-general · gemini-2.0-flash

    explaining or clarifying statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﹧
    -0.69
    parsedMessage
    -0.68
     パンチラ
    -0.68
     queſta
    -0.66
     للمعارف
    -0.66
    <unused3>
    -0.66
    <unused14>
    -0.65
    <unused43>
    -0.65
    [@BOS@]
    -0.65
    <pad>
    -0.65
    POSITIVE LOGITS
    :
    0.61
    ,
    0.59
    ;
    0.54
    .
    0.47
     -
    0.43
     in
    0.42
     if
    0.41
     as
    0.40
     --
    0.38
     –
    0.38
    Act Density 0.420%

    No Known Activations