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

    Neuronpedia

    INDEX
    Explanations

    locations or distances from specific landmarks or borders

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meantime
    -0.64
     deft
    -0.62
     backward
    -0.62
     sparing
    -0.62
     wisely
    -0.61
     McKin
    -0.61
    ãĤ°
    -0.61
     retro
    -0.60
    Reply
    -0.60
     adapt
    -0.59
    POSITIVE LOGITS
     entrance
    0.88
     horizon
    0.86
     sidx
    0.85
    antage
    0.81
     boundaries
    0.78
    ulkan
    0.78
     station
    0.77
     boundary
    0.76
     headquarters
    0.75
     checkpoint
    0.75
    Act Density 0.519%

    No Known Activations