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

    Neuronpedia

    INDEX
    Explanations

    names of places or establishments, potentially in foreign languages

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or unusual characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.94
     contrace
    -0.90
    etheless
    -0.86
    sembly
    -0.84
     livest
    -0.80
    ftime
    -0.79
    ntil
    -0.79
     proble
    -0.78
    anwhile
    -0.78
     confir
    -0.77
    POSITIVE LOGITS
    è
    2.01
    æ
    2.01
    å¸
    2.00
    ç
    1.98
    åĬ
    1.96
    é
    1.95
    åį
    1.92
    å
    1.91
    éĩ
    1.90
    人
    1.89
    Act Density 0.039%

    No Known Activations