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

    Neuronpedia

    INDEX
    Explanations

    references to compatibility or suitability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.72
    parsedMessage
    -0.62
     InputDecoration
    -0.62
     ainfi
    -0.60
     パンチラ
    -0.60
     NSCoder
    -0.59
    <unused28>
    -0.59
    <unused23>
    -0.59
    [@BOS@]
    -0.59
    <unused14>
    -0.59
    POSITIVE LOGITS
     suit
    0.83
     suited
    0.76
     suits
    0.69
     suitable
    0.68
    suit
    0.65
     Hel
    0.57
    suitable
    0.57
    suits
    0.55
    suited
    0.54
     suitability
    0.53
    Act Density 0.262%

    No Known Activations