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

    Neuronpedia

    INDEX
    Explanations

    country names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dialogue
    -0.68
    locks
    -0.67
     Sunday
    -0.65
     Wednesday
    -0.64
    Patch
    -0.62
     [...]
    -0.62
     msec
    -0.61
     Veterinary
    -0.61
     Combat
    -0.60
     Environment
    -0.60
    POSITIVE LOGITS
    Ĥª
    0.77
     rul
    0.76
     advoc
    0.71
    ij士
    0.70
    çİĭ
    0.69
    auri
    0.68
    ļé
    0.66
    eters
    0.64
    govern
    0.64
     unfocusedRange
    0.64
    Act Density 0.000%

    No Known Activations