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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or states of intensity or significance

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions that imply manipulation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.68
    unknown
    -0.52
    rag
    -0.51
    href
    -0.48
     suppose
    -0.48
    microsoft
    -0.48
    adr
    -0.48
    plom
    -0.47
    ridor
    -0.47
    DragonMagazine
    -0.47
    POSITIVE LOGITS
    lessly
    0.67
    ulate
    0.66
    uate
    0.66
    ibly
    0.65
    fully
    0.65
    ishly
    0.62
    matically
    0.62
    aciously
    0.57
    bably
    0.56
    ify
    0.56
    Act Density 0.638%

    No Known Activations