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

    Neuronpedia

    INDEX
    Explanations

    prepositions related to movement or transportation

    oai_token-act-pair · gpt-3.5-turbo

    references to transportation methods and destinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strong
    -0.71
    idav
    -0.67
    woman
    -0.66
    etheless
    -0.64
    ussion
    -0.61
    alion
    -0.60
    angered
    -0.60
    allion
    -0.60
     Recorded
    -0.59
    mask
    -0.58
    POSITIVE LOGITS
     destinations
    1.15
     places
    0.91
     avoid
    0.89
     wherever
    0.88
     maximize
    0.88
    ggles
    0.88
     meet
    0.88
    pless
    0.84
     satisfy
    0.84
     relieve
    0.83
    Act Density 0.169%

    No Known Activations