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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, possibly related to locations, entities, or names

    oai_token-act-pair · gpt-3.5-turbo

    unconventional characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.97
    etheless
    -0.96
    anwhile
    -0.84
     contrace
    -0.84
    abase
    -0.81
     skelet
    -0.79
    ftime
    -0.79
    ebus
    -0.78
     srf
    -0.77
    undai
    -0.76
    POSITIVE LOGITS
    å
    1.33
    å¸
    1.33
    çĶ°
    1.32
    ç
    1.30
    ãģ®å
    1.29
    é¾į
    1.29
    âĢİ
    1.26
    ãĤ
    1.26
    è
    1.26
    æ
    1.25
    Act Density 0.058%

    No Known Activations