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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns related to locations or people

    oai_token-act-pair · gpt-3.5-turbo

    references to the Canary Islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ration
    -0.94
    rolled
    -0.93
    issance
    -0.82
    rative
    -0.81
    mission
    -0.77
    esc
    -0.77
    rity
    -0.77
    hes
    -0.76
    mit
    -0.76
    email
    -0.73
    POSITIVE LOGITS
     Canary
    1.29
     BaseType
    0.89
     Languages
    0.78
     subp
    0.76
     Lower
    0.74
     Commands
    0.73
     âĸº
    0.72
    Ø©
    0.71
     Idle
    0.70
    æ©Ł
    0.70
    Act Density 0.032%

    No Known Activations