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

    Neuronpedia

    INDEX
    Explanations

    specific physical locations

    oai_token-act-pair · gpt-3.5-turbo

    locations and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.71
     obliged
    -0.67
     confir
    -0.67
     fuelled
    -0.67
    fights
    -0.66
    HTTP
    -0.65
     behaviours
    -0.63
    xual
    -0.63
     traged
    -0.63
    etheless
    -0.62
    POSITIVE LOGITS
    rium
    1.25
     701
    1.23
     601
    1.20
     2100
    1.18
     505
    1.14
     2600
    1.13
     702
    1.12
     620
    1.11
     501
    1.11
     610
    1.10
    Act Density 0.128%

    No Known Activations