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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to different locations, events, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names of places and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icably
    -0.82
    icable
    -0.78
    enance
    -0.78
    alty
    -0.77
     allowable
    -0.75
    isable
    -0.71
     relativity
    -0.71
     oblig
    -0.70
     captcha
    -0.69
    urable
    -0.69
    POSITIVE LOGITS
     Bowl
    1.09
     Creek
    1.05
     Island
    1.02
     Grove
    1.02
     Soup
    0.97
    Dog
    0.96
     Valley
    0.95
     Dogs
    0.95
     Islands
    0.94
     Wars
    0.94
    Act Density 0.304%

    No Known Activations