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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "then" indicating a sequence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leban
    -0.16
    uali
    -0.15
    osl
    -0.15
    leet
    -0.15
    ãĤ¡
    -0.15
    tır
    -0.15
    ienda
    -0.14
    thora
    -0.14
    oslav
    -0.14
    amba
    -0.14
    POSITIVE LOGITS
    mate
    0.16
    phan
    0.14
    iga
    0.14
     entire
    0.14
    ews
    0.14
    ewis
    0.14
     Hib
    0.14
     dne
    0.13
    eses
    0.13
     Davies
    0.13
    Act Density 0.065%

    No Known Activations