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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or prompts to click on links

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions suggesting interaction or engagement with content, such as reading or viewing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edom
    -0.74
    phony
    -0.74
    existence
    -0.73
    transform
    -0.71
    é¾įåĸļ士
    -0.70
    beit
    -0.68
    edIn
    -0.67
    Cons
    -0.67
    phen
    -0.66
    existent
    -0.65
    POSITIVE LOGITS
     enlarge
    1.11
     link
    0.90
     enlarg
    0.85
     LINK
    0.85
     gallery
    0.83
     subscribe
    0.82
     download
    0.82
     pdf
    0.78
     PDF
    0.76
     enlarged
    0.75
    Act Density 0.052%

    No Known Activations