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

    Neuronpedia

    INDEX
    Explanations

    references to specific names, titles, or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jacob
    -0.17
    Jacob
    -0.16
     Mariners
    -0.16
    acob
    -0.15
    TERN
    -0.14
     Hartford
    -0.14
     Cherokee
    -0.14
    ofire
    -0.14
     Jacobs
    -0.14
    koli
    -0.14
    POSITIVE LOGITS
     Kub
    0.34
     Alex
    0.33
    Alex
    0.26
     Stanley
    0.26
     Burgess
    0.25
     dro
    0.23
     Alexand
    0.23
     ÐIJлекÑģ
    0.23
     Aleks
    0.23
     Alexander
    0.22
    Act Density 0.006%

    No Known Activations