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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or requests for clarification

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

    Preceding words of "correct" or "wrong."

    np_acts-logits-general · gemini-2.0-flash

    correctness or incorrectness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.66
    MLLoader
    -0.57
    SourceChecksum
    -0.53
    +#+#
    -0.51
     ProtoMessage
    -0.47
    UniformLocation
    -0.47
    érables
    -0.46
    useNewUrlParser
    -0.46
    PropertyChanging
    -0.46
    DataMember
    -0.45
    POSITIVE LOGITS
     correct
    2.79
    correct
    2.46
     correctly
    2.45
     Correct
    2.41
    Correct
    2.40
     wrong
    2.39
     incorrect
    2.10
     CORRECT
    2.07
    wrong
    2.06
    correctly
    2.03
    Act Density 0.602%

    No Known Activations