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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names, potentially related to a specific person or place

    oai_token-act-pair · gpt-3.5-turbo

    the word "ano" which is likely indicative of discussions related to the year or events associated with specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.97
    owship
    -0.83
    brain
    -0.76
    tered
    -0.74
     glim
    -0.71
    mented
    -0.69
    ties
    -0.69
    drawn
    -0.68
    respective
    -0.68
    monton
    -0.67
    POSITIVE LOGITS
    jo
    1.19
    zzi
    1.13
    qua
    0.94
    zzo
    0.94
    zo
    0.92
    ose
    0.90
    hazard
    0.89
    eli
    0.88
    ahu
    0.86
    ichi
    0.84
    Act Density 0.024%

    No Known Activations