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

    Neuronpedia

    INDEX
    Explanations

    the word "bumble" followed by a number indicating the strength of a match

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand "Bumble."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.89
    ablishment
    -0.83
    ohn
    -0.81
    ning
    -0.80
    nesota
    -0.78
    asel
    -0.72
    fman
    -0.72
    atural
    -0.69
    itutional
    -0.68
    pherd
    -0.68
    POSITIVE LOGITS
    weed
    1.00
    bee
    0.90
    bles
    0.88
    bly
    0.86
     Bundle
    0.85
    ble
    0.82
     Bee
    0.79
    grass
    0.78
    bees
    0.78
    BLE
    0.77
    Act Density 0.010%

    No Known Activations