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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fallen
    -0.16
    دÙĬ
    -0.16
    leck
    -0.15
    uzzi
    -0.15
     ridden
    -0.14
     Lage
    -0.14
    ewire
    -0.14
     sooner
    -0.14
    ovation
    -0.14
    æŀ
    -0.14
    POSITIVE LOGITS
     Pul
    0.28
     Ke
    0.26
     Ta
    0.25
     Bro
    0.22
     Sp
    0.22
     Shared
    0.21
     Open
    0.21
     Ran
    0.20
     Drew
    0.20
     Met
    0.20
    Act Density 0.211%

    No Known Activations