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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Waters."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oard
    -0.71
    ERAL
    -0.70
    bable
    -0.70
    unal
    -0.70
     centralized
    -0.70
    ĻĤ
    -0.67
     Haiti
    -0.64
     prisoner
    -0.64
    uster
    -0.64
    OTS
    -0.63
    POSITIVE LOGITS
     Waters
    1.45
    waters
    0.95
    melon
    0.94
    cape
    0.87
    geist
    0.87
    combe
    0.86
    boro
    0.86
    hed
    0.83
    water
    0.81
    Cry
    0.81
    Act Density 0.004%

    No Known Activations