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

    Neuronpedia

    INDEX
    Explanations

    mentions of forum threads and guidelines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "thread" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.69
     plaintiffs
    -0.69
    cers
    -0.69
     Defenders
    -0.68
    kef
    -0.68
     Plaint
    -0.65
    inez
    -0.65
    emy
    -0.64
     Nikki
    -0.64
    cé
    -0.63
    POSITIVE LOGITS
    bare
    1.52
    thread
    1.22
     thread
    1.21
     threads
    1.05
     Thread
    0.93
    worms
    0.87
    need
    0.86
    worm
    0.86
    stack
    0.82
    lock
    0.81
    Act Density 0.012%

    No Known Activations