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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, especially related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations or names related to cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.79
    ge
    -0.77
    cho
    -0.76
    course
    -0.75
    itions
    -0.74
    odd
    -0.73
    burning
    -0.71
    treatment
    -0.71
    sys
    -0.69
    ok
    -0.69
    POSITIVE LOGITS
    URA
    1.14
     GEAR
    1.10
    LAND
    1.09
     ANGEL
    1.09
     EDITION
    1.06
    LEASE
    1.05
    STON
    1.04
    INESS
    1.04
     IMAGES
    1.04
    ANCE
    1.03
    Act Density 0.039%

    No Known Activations