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

    Neuronpedia

    INDEX
    Explanations

    words ending in "ow"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ually
    -0.83
     capsule
    -0.69
     locality
    -0.68
     suspic
    -0.67
     siph
    -0.66
     pinch
    -0.65
    ãĥ¼ãĥĨ
    -0.63
    £ı
    -0.63
    âĶģ
    -0.62
     abduct
    -0.60
    POSITIVE LOGITS
    orld
    1.34
    ards
    1.09
    itsch
    1.05
    olves
    0.97
    een
    0.96
    riter
    0.96
    idth
    0.94
    restling
    0.92
    atts
    0.91
    ood
    0.90
    Act Density 0.040%

    No Known Activations