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

    Neuronpedia

    INDEX
    Explanations

    mentions of the phrase "GO" followed by a numerical value from 6 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to a transit system called the GO Train

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icio
    -0.75
    ienced
    -0.72
    acters
    -0.67
    manship
    -0.65
    creen
    -0.65
    chers
    -0.63
    ussen
    -0.62
    dimension
    -0.62
     Jed
    -0.60
    uracy
    -0.60
    POSITIVE LOGITS
    GO
    1.13
    vernment
    0.91
     GO
    0.90
    VER
    0.90
    XL
    0.88
    VE
    0.86
    ALS
    0.84
    UE
    0.82
    FOR
    0.79
    ARCH
    0.79
    Act Density 0.008%

    No Known Activations