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

    Neuronpedia

    INDEX
    Explanations

    locations and positions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opi
    -0.16
    ibase
    -0.15
    oven
    -0.15
    -pocket
    -0.15
     tunnels
    -0.15
    ighton
    -0.14
    rift
    -0.14
     klu
    -0.14
    ocket
    -0.13
    atti
    -0.13
    POSITIVE LOGITS
     platform
    0.29
     platforms
    0.28
     bench
    0.27
    platform
    0.26
     steps
    0.26
     stool
    0.25
     PLATFORM
    0.23
     balcony
    0.23
     Platform
    0.22
     plataforma
    0.22
    Act Density 0.193%

    No Known Activations