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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "ble"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ble."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancial
    -0.70
    doms
    -0.69
    erva
    -0.68
     Ernst
    -0.68
    ahime
    -0.67
    ammad
    -0.65
    ellar
    -0.65
    AMI
    -0.64
     ACTIONS
    -0.62
    alli
    -0.62
    POSITIVE LOGITS
    ble
    1.31
    bles
    1.31
    bled
    1.02
    bling
    1.01
    bly
    0.94
    tt
    0.81
    bum
    0.80
    ede
    0.77
    vous
    0.77
    ogle
    0.76
    Act Density 0.007%

    No Known Activations