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

    Neuronpedia

    INDEX
    Explanations

    phrases related to traveling to different locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating travel or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    need
    -0.75
    natureconservancy
    -0.67
    */(
    -0.67
    pie
    -0.66
     ramifications
    -0.66
     levied
    -0.65
     stru
    -0.65
    attribute
    -0.65
     handled
    -0.64
     payable
    -0.63
    POSITIVE LOGITS
    pload
    0.98
     Disneyland
    0.89
     Liberia
    0.85
    ilet
    0.83
     shore
    0.81
     Omaha
    0.80
     fulfill
    0.80
     relieve
    0.79
     commemorate
    0.79
     visit
    0.79
    Act Density 0.288%

    No Known Activations