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

    Neuronpedia

    INDEX
    Explanations

    specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.79
    ights
    -0.78
    tails
    -0.74
    unes
    -0.74
    jin
    -0.74
    tail
    -0.73
    kos
    -0.73
    alin
    -0.68
    und
    -0.67
    ylan
    -0.67
    POSITIVE LOGITS
     location
    1.31
     locations
    1.17
    location
    0.92
     Location
    0.88
     locate
    0.84
     Locations
    0.83
     locality
    0.82
     signage
    0.80
     locating
    0.75
     relocation
    0.75
    Act Density 0.011%

    No Known Activations