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

    Neuronpedia

    INDEX
    Explanations

    words containing the substring 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles ending in "ing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Columb
    -0.66
     COURT
    -0.61
    å£
    -0.60
    ãĥŀ
    -0.59
    ngth
    -0.58
     bount
    -0.58
     butterflies
    -0.56
     Archangel
    -0.56
     Horowitz
    -0.56
     desks
    -0.56
    POSITIVE LOGITS
    redients
    1.11
    tons
    0.98
    lass
    0.95
    rill
    0.95
    roup
    0.91
    orah
    0.89
    hai
    0.87
    yi
    0.85
    ulum
    0.82
    lasses
    0.82
    Act Density 0.063%

    No Known Activations