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

    Neuronpedia

    INDEX
    Explanations

    mentions of thread-related technical terms and programming language functions

    oai_token-act-pair · gpt-3.5-turbo

    references to threads in programming or computing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.77
    kef
    -0.74
    cers
    -0.70
     Defenders
    -0.68
    cé
    -0.64
    cer
    -0.62
    mosp
    -0.61
     caric
    -0.61
     Nikki
    -0.61
     Burnett
    -0.60
    POSITIVE LOGITS
    bare
    1.58
    thread
    1.13
     thread
    1.12
     threads
    1.01
    need
    0.99
    ming
    0.89
     Thread
    0.88
    shed
    0.82
    ioned
    0.82
    ing
    0.81
    Act Density 0.016%

    No Known Activations