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

    Neuronpedia

    INDEX
    Explanations

    mentions of travel or movement

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "travel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liga
    -0.82
    corn
    -0.78
    cher
    -0.76
    arist
    -0.73
    reme
    -0.68
    sei
    -0.64
    pta
    -0.64
    aminer
    -0.62
    arov
    -0.62
    argon
    -0.61
    POSITIVE LOGITS
     abroad
    0.92
     Trave
    0.86
     traveled
    0.82
    ogue
    0.80
     itiner
    0.80
     travel
    0.79
    agy
    0.75
     extensively
    0.75
    aughs
    0.74
     travelled
    0.73
    Act Density 0.029%

    No Known Activations