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

    Neuronpedia

    INDEX
    Explanations

    indicators of message validation or error reporting

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

    error or translation messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.60
     CreateTagHelper
    -0.59
    OGND
    -0.56
    :✨
    -0.52
    WireFormatLite
    -0.51
     houſe
    -0.51
    AnchorStyles
    -0.50
    queryInterface
    -0.50
    PreferredItem
    -0.50
    קישורים
    -0.50
    POSITIVE LOGITS
    relativeTime
    0.49
    astify
    0.45
     statement
    0.44
    PyExc
    0.42
    VersionUID
    0.39
     worded
    0.38
    makeText
    0.37
    świ
    0.37
    PyErr
    0.37
    lbl
    0.36
    Act Density 0.030%

    No Known Activations