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

    Neuronpedia

    INDEX
    Explanations

    references to societal concepts, structures, and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orie
    -0.19
    otty
    -0.15
    oge
    -0.15
    andes
    -0.15
    oria
    -0.14
    elow
    -0.14
    иÑĢов
    -0.14
     Downing
    -0.14
    ysis
    -0.14
    dater
    -0.14
    POSITIVE LOGITS
    -wide
    0.32
    wide
    0.26
    /community
    0.21
    /world
    0.19
     wide
    0.19
    Wide
    0.17
     norms
    0.16
    /media
    0.16
    /system
    0.15
    hood
    0.15
    Act Density 0.034%

    No Known Activations