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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating involvement or participation in an activity

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating involvement or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.68
    tip
    -0.67
    acebook
    -0.67
    enegger
    -0.65
    sers
    -0.64
     Saga
    -0.63
    illac
    -0.63
    eday
    -0.61
     Starship
    -0.61
    lete
    -0.60
    POSITIVE LOGITS
    cre
    0.73
    asonic
    0.70
     hurry
    0.70
    rob
    0.63
    ricular
    0.62
    Area
    0.60
     shootout
    0.59
     bedrooms
    0.59
    ucl
    0.58
    naires
    0.57
    Act Density 0.129%

    No Known Activations