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

    Neuronpedia

    INDEX
    Explanations

    words ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.66
    ufact
    -0.63
    vier
    -0.62
     Powered
    -0.61
     underpin
    -0.61
    ivari
    -0.61
    è£ħ
    -0.59
     Strong
    -0.59
     Register
    -0.58
     fue
    -0.57
    POSITIVE LOGITS
    redients
    1.09
    lishes
    0.76
    tons
    0.76
    ulate
    0.74
    ially
    0.69
    entin
    0.68
    OTUS
    0.66
    borough
    0.66
    LY
    0.66
    aukee
    0.65
    Act Density 0.082%

    No Known Activations