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

    Neuronpedia

    INDEX
    Explanations

    unique patterns of uppercase letters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "OM"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wall
    -0.81
    hs
    -0.76
    issance
    -0.72
    chnology
    -0.69
    ience
    -0.69
    connected
    -0.67
    ivities
    -0.66
    forcing
    -0.65
    ually
    -0.64
     juices
    -0.62
    POSITIVE LOGITS
    EGA
    1.02
    orrow
    0.90
    ENA
    0.87
    ESA
    0.86
    BAT
    0.82
    AX
    0.81
    ETH
    0.81
    BO
    0.80
    MU
    0.80
    ISSION
    0.79
    Act Density 0.024%

    No Known Activations