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

    Neuronpedia

    INDEX
    Explanations

    functions related to outputting error messages or logging

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

    function calls that output error messages to the standard error stream

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

    fprintf calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bear
    -0.60
    :+:
    -0.53
    AsUp
    -0.52
     وسلم
    -0.52
     ​​
    -0.48
    bear
    -0.47
    addLast
    -0.47
    ьаж
    -0.45
    لاثة
    -0.45
     si
    -0.45
    POSITIVE LOGITS
     Efq
    0.97
     myſelf
    0.96
     Anſ
    0.94
     Majefty
    0.94
     Monfieur
    0.92
     houſe
    0.91
     diſt
    0.89
     purpoſe
    0.89
     iſt
    0.89
     Houſe
    0.88
    Act Density 0.013%

    No Known Activations