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

    Neuronpedia

    INDEX
    Explanations

    words related to software or technology threads

    oai_token-act-pair · gpt-3.5-turbo

    references to threads in programming or discussions about multithreading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cers
    -0.75
    kef
    -0.73
     Defenders
    -0.67
    cer
    -0.66
     Flavoring
    -0.66
    cé
    -0.62
     unaff
    -0.61
     Suc
    -0.61
     lett
    -0.60
     judgments
    -0.60
    POSITIVE LOGITS
    bare
    1.57
     thread
    1.18
    thread
    1.17
     threads
    1.10
    need
    0.99
     Thread
    0.96
    heads
    0.83
    pool
    0.82
    ming
    0.81
    crew
    0.79
    Act Density 0.022%

    No Known Activations