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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters at specific locations within text sequences

    oai_token-act-pair · gpt-3.5-turbo

    statements that express opinions or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.71
    ensibly
    -0.63
    aeda
    -0.62
     Reincarnated
    -0.61
     proport
    -0.58
    abouts
    -0.57
     citiz
    -0.57
    mbuds
    -0.56
    sterdam
    -0.56
    bags
    -0.56
    POSITIVE LOGITS
    "(
    0.88
    "
    0.78
    "[
    0.73
     "(
    0.72
    "...
    0.72
    "-
    0.71
     "'
    0.71
    He
    0.68
     "[
    0.66
    "'
    0.65
    Act Density 0.338%

    No Known Activations