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

    Neuronpedia

    INDEX
    Explanations

    references to popular media, specifically related to television and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quate
    -0.15
    йн
    -0.15
     split
    -0.15
    isto
    -0.14
    缸
    -0.14
     Bolt
    -0.14
     fox
    -0.14
    383
    -0.14
     Arabia
    -0.14
    'gc
    -0.14
    POSITIVE LOGITS
     Stranger
    0.20
    Netflix
    0.20
     Hawkins
    0.20
     Netflix
    0.20
    ackbar
    0.17
    овоÑĢ
    0.16
    Wunused
    0.16
    çķ
    0.16
    egov
    0.16
    .ci
    0.15
    Act Density 0.025%

    No Known Activations