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

    Neuronpedia

    INDEX
    Explanations

    Filipino phrases or sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to language and communication, particularly in a specific cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quished
    -0.81
    Redd
    -0.81
    External
    -0.79
    CLASSIFIED
    -0.79
    auld
    -0.78
    oresc
    -0.75
    ernels
    -0.74
    00007
    -0.74
    Rex
    -0.74
    VIDIA
    -0.74
    POSITIVE LOGITS
     lang
    0.91
     tha
    0.86
     pu
    0.76
     ta
    0.76
     pa
    0.75
     n
    0.73
     los
    0.73
     mah
    0.72
     princip
    0.69
     nar
    0.69
    Act Density 0.292%

    No Known Activations