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

    Neuronpedia

    INDEX
    Explanations

    keywords related to an interactive platform named "PaperHive"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ive"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.70
    adra
    -0.69
    ascript
    -0.69
    akra
    -0.68
    EXP
    -0.67
    ItemTracker
    -0.66
    naires
    -0.65
    mouth
    -0.63
    afort
    -0.63
    ortmund
    -0.63
    POSITIVE LOGITS
    ived
    0.79
    ive
    0.79
     Soy
    0.72
    bye
    0.70
     Canad
    0.67
    rics
    0.66
    cade
    0.65
    locking
    0.63
    cery
    0.61
     hail
    0.61
    Act Density 0.018%

    No Known Activations