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

    Neuronpedia

    INDEX
    Explanations

    destination-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to places or locations identified as destinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appa
    -0.94
    croft
    -0.83
    IGHTS
    -0.83
    aps
    -0.82
    ooks
    -0.73
    ells
    -0.72
    ucket
    -0.72
    erd
    -0.71
    opes
    -0.70
    andro
    -0.70
    POSITIVE LOGITS
     Destination
    1.25
     destination
    1.21
     destinations
    1.04
     Afric
    0.72
    ãĥķãĤ©
    0.71
     Kuala
    0.71
     haunt
    0.70
     traveler
    0.70
     location
    0.70
    Disney
    0.69
    Act Density 0.006%

    No Known Activations