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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.66
    UnitTesting
    -0.65
     Wiktionnaire
    -0.61
    TypedDataSet
    -0.60
    MessageState
    -0.54
     pinulongan
    -0.54
     Constitucional
    -0.54
     PopupWindow
    -0.54
    tahui
    -0.54
    postIndex
    -0.53
    POSITIVE LOGITS
     why
    0.56
     what
    0.53
     WTF
    0.53
    why
    0.52
     how
    0.51
    wtf
    0.50
     WHY
    0.49
     Why
    0.49
     wtf
    0.48
    what
    0.48
    Act Density 0.004%

    No Known Activations