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

    Neuronpedia

    INDEX
    Explanations

    verbs ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ve."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atural
    -0.66
    selves
    -0.59
     flash
    -0.59
     iPhones
    -0.59
    ority
    -0.58
     optionally
    -0.57
     rook
    -0.56
     affiliation
    -0.56
     handlers
    -0.55
     offsets
    -0.55
    POSITIVE LOGITS
    illance
    1.42
    ttes
    1.24
    tsky
    1.22
    tti
    1.19
    llers
    1.19
    ller
    1.14
    lling
    1.14
    lla
    1.14
    tta
    1.13
    tt
    1.12
    Act Density 0.038%

    No Known Activations