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

    Neuronpedia

    INDEX
    Explanations

    numerical values or technical information

    oai_token-act-pair · gpt-3.5-turbo

    patterns of repeated characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iller
    -0.74
    hai
    -0.70
     Canad
    -0.70
    illary
    -0.69
    illed
    -0.68
     Kitt
    -0.68
     Bridgewater
    -0.68
     Afric
    -0.66
     Pilgrim
    -0.63
    pher
    -0.63
    POSITIVE LOGITS
    ------------
    1.30
    ======
    1.28
    ---------
    1.27
    ====
    1.27
    ---------------
    1.26
    ______
    1.26
    -------------
    1.24
    ============
    1.23
    _______
    1.21
    ___
    1.20
    Act Density 0.029%

    No Known Activations