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

    Neuronpedia

    INDEX
    Explanations

    cliché and recurring phrases used in various written texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express consistency or routine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arag
    -0.75
    kefeller
    -0.72
    abases
    -0.72
    anyon
    -0.71
    eways
    -0.70
    agra
    -0.70
    medium
    -0.67
    fram
    -0.67
    estyle
    -0.67
    glers
    -0.67
    POSITIVE LOGITS
     disclaim
    0.79
     disclaimer
    0.71
     wont
    0.71
    ________________________________________________________________
    0.65
     Spoiler
    0.64
     happens
    0.63
     Sunny
    0.63
     dividends
    0.62
    NP
    0.60
     fav
    0.60
    Act Density 0.040%

    No Known Activations