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

    Neuronpedia

    INDEX
    Explanations

    programming syntax-related terms

    oai_token-act-pair · gpt-3.5-turbo

    strings that are formatted as underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quished
    -0.81
     Garry
    -0.78
     Casey
    -0.77
     Leilan
    -0.77
     JPM
    -0.77
     Pearce
    -0.77
     Mercy
    -0.76
     Xavier
    -0.74
     Eggs
    -0.73
    eteria
    -0.72
    POSITIVE LOGITS
    dict
    1.07
    blank
    1.06
    gradient
    1.02
    page
    1.00
    prefix
    1.00
    modules
    0.99
    default
    0.99
    chance
    0.98
    title
    0.98
    location
    0.98
    Act Density 0.025%

    No Known Activations