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 (words ending in 'ing')

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.75
    luaj
    -0.74
    ivari
    -0.67
    ufact
    -0.63
    Neg
    -0.63
     Shooter
    -0.62
    å£
    -0.60
    ascript
    -0.58
    IFIC
    -0.58
    ngth
    -0.58
    POSITIVE LOGITS
    redients
    1.24
    tons
    1.11
    ales
    0.75
    borough
    0.72
    ially
    0.71
    ered
    0.71
    ication
    0.70
    athering
    0.70
     Nazis
    0.70
    ding
    0.69
    Act Density 0.076%

    No Known Activations