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

    Neuronpedia

    INDEX
    Explanations

    numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    repeated patterns of punctuation or numerical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uggest
    -0.65
    ngth
    -0.65
     melanch
    -0.64
     fantasies
    -0.58
     reconc
    -0.58
     gad
    -0.58
     vag
    -0.55
     Cros
    -0.55
    ioned
    -0.55
    ashtra
    -0.54
    POSITIVE LOGITS
    000
    1.13
    00
    0.98
    9
    0.97
    0
    0.93
    8
    0.91
    6
    0.90
    048
    0.89
    12
    0.88
    600
    0.88
    09
    0.86
    Act Density 0.110%

    No Known Activations