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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or titles with specific structure

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names related to entities, possibly in a political or historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.82
    姫
    -0.80
    Ô
    -0.79
     weap
    -0.75
    abwe
    -0.74
    ä
    -0.74
    é¾įå¥ij士
    -0.72
     sqor
    -0.71
    inventoryQuantity
    -0.71
     matt
    -0.69
    POSITIVE LOGITS
    iest
    0.91
    agame
    0.83
    hest
    0.83
    isphere
    0.82
    osphere
    0.80
    ariat
    0.77
    venth
    0.76
    owment
    0.75
     Legislature
    0.75
    cients
    0.74
    Act Density 0.280%

    No Known Activations