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

    Neuronpedia

    INDEX
    Explanations

    strings with a specific format including non-alphabetical characters

    oai_token-act-pair · gpt-3.5-turbo

    references to video games or gaming-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dek
    -0.82
     Advantage
    -0.75
    tsky
    -0.71
     undermin
    -0.70
    scill
    -0.68
     disadvant
    -0.68
     unlaw
    -0.67
     Oo
    -0.66
     Tokens
    -0.65
     Rewards
    -0.64
    POSITIVE LOGITS
    manager
    0.82
    info
    0.74
    editor
    0.73
    ping
    0.72
    server
    0.71
    @
    0.71
    json
    0.70
    database
    0.70
    rw
    0.70
    global
    0.69
    Act Density 0.478%

    No Known Activations