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

    Neuronpedia

    INDEX
    Explanations

    references to British institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orgh
    -0.17
    itu
    -0.15
    formed
    -0.14
    åħ±åĴĮåĽ½
    -0.14
    agher
    -0.14
    inator
    -0.14
    åĺ
    -0.14
     "-//
    -0.14
    integral
    -0.14
    otime
    -0.13
    POSITIVE LOGITS
     Isles
    0.36
     Columbia
    0.36
     Airways
    0.23
     Colum
    0.23
    olumbia
    0.22
    ness
    0.21
     Virgin
    0.20
     Empire
    0.20
     Colombia
    0.20
     Raj
    0.19
    Act Density 0.022%

    No Known Activations