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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing social structures and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sez
    -0.18
     надо
    -0.18
    Anyway
    -0.17
    IMO
    -0.16
    oka
    -0.16
    OK
    -0.15
     marshal
    -0.15
    å¹²
    -0.14
     praž
    -0.14
    ledon
    -0.14
    POSITIVE LOGITS
     heavily
    0.20
     solely
    0.18
     vocal
    0.18
     continuously
    0.17
     util
    0.17
     abst
    0.17
     Util
    0.16
    SizePolicy
    0.16
     ult
    0.16
     oft
    0.16
    Act Density 0.568%

    No Known Activations