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

    Neuronpedia

    INDEX
    Explanations

    instances of travel-related actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to travel and destinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rag
    -0.75
     Minutes
    -0.66
    arth
    -0.65
    anity
    -0.65
    Rating
    -0.65
    allic
    -0.64
    inctions
    -0.64
     unison
    -0.64
    hands
    -0.63
    interstitial
    -0.63
    POSITIVE LOGITS
     vacation
    0.86
     tourist
    0.86
     befriend
    0.83
     resid
    0.80
    quartered
    0.78
     exile
    0.76
     refugee
    0.76
     vacations
    0.75
    irlf
    0.75
     abroad
    0.73
    Act Density 0.529%

    No Known Activations