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

    Neuronpedia

    INDEX
    Explanations

    Filipino language phrases

    oai_token-act-pair · gpt-3.5-turbo

    language and cultural references, particularly in a specific context or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.87
    furt
    -0.83
    ologne
    -0.78
    quished
    -0.78
    CLASSIFIED
    -0.77
     Zurich
    -0.74
    emort
    -0.70
    RIC
    -0.70
    ifix
    -0.70
    avier
    -0.68
    POSITIVE LOGITS
     Hindi
    0.87
    ahi
    0.86
     ki
    0.85
    iya
    0.79
     lang
    0.79
     mah
    0.76
     ka
    0.75
     na
    0.75
     kay
    0.75
    ',"
    0.74
    Act Density 0.130%

    No Known Activations