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

    Neuronpedia

    INDEX
    Explanations

    references to blood vessels

    oai_token-act-pair · gpt-3.5-turbo

    references to blood vessels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bread
    -0.71
    iaries
    -0.71
    -+-+-+-+
    -0.71
    heimer
    -0.70
    ety
    -0.70
    arton
    -0.69
    enhagen
    -0.69
    iary
    -0.66
    orph
    -0.66
    organic
    -0.66
    POSITIVE LOGITS
     vessels
    1.25
     vessel
    1.22
     Vessel
    1.03
     reefs
    0.77
     fleet
    0.75
     HMS
    0.72
     Yamato
    0.71
     reef
    0.71
     boats
    0.71
     Voy
    0.69
    Act Density 0.033%

    No Known Activations