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

    Neuronpedia

    INDEX
    Explanations

    words related to rapid change or transition

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating rapid change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preserved
    -0.61
     implicit
    -0.61
     Declaration
    -0.58
     Contra
    -0.58
     preserving
    -0.57
     millenn
    -0.57
     remnant
    -0.57
    cius
    -0.57
     Moor
    -0.57
    matically
    -0.57
    POSITIVE LOGITS
    ounters
    0.86
    ibaba
    0.85
    enges
    0.75
    ependence
    0.74
    mega
    0.74
    agues
    0.73
    Ô
    0.73
    ãĤ¼ãĤ¦ãĤ¹
    0.72
    steen
    0.72
    argon
    0.70
    Act Density 0.240%

    No Known Activations