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

    Neuronpedia

    INDEX
    Explanations

    dialogue related to introductions and greetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ughs
    -0.16
     je
    -0.15
    pawn
    -0.15
    outes
    -0.15
    aina
    -0.15
    PEG
    -0.15
     Gram
    -0.14
     gram
    -0.14
    993
    -0.14
    ĨĴ
    -0.14
    POSITIVE LOGITS
     handshake
    0.25
    æı¡
    0.19
     introdu
    0.17
     Introduced
    0.17
     shake
    0.17
    å¯Ĵ
    0.16
     shakes
    0.16
     introduce
    0.15
     ExecutionContext
    0.15
    ãĥŃãĥ³
    0.15
    Act Density 0.146%

    No Known Activations