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

    Neuronpedia

    INDEX
    Explanations

    words containing the suffix "-ing"

    oai_token-act-pair · gpt-3.5-turbo

    progressive verb forms ending in "ing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.69
    å£
    -0.68
    ascript
    -0.67
    osate
    -0.64
    ihar
    -0.62
    aternal
    -0.62
     Columb
    -0.61
     Leilan
    -0.61
    ãĥ¤
    -0.60
    ascade
    -0.60
    POSITIVE LOGITS
    redients
    1.28
    tons
    1.20
    lass
    1.08
    ham
    0.93
    lasses
    0.88
    hoff
    0.86
    roup
    0.84
    hetti
    0.84
    rad
    0.84
    uez
    0.83
    Act Density 0.049%

    No Known Activations