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

    Neuronpedia

    INDEX
    Explanations

    names of locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic locations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.70
     ..."
    -0.67
     âĢ¦"
    -0.65
    ··
    -0.64
    ̶
    -0.62
     thereto
    -0.62
     opposite
    -0.59
    ο
    -0.58
    .</
    -0.57
     ])
    -0.56
    POSITIVE LOGITS
    theless
    0.91
    anyahu
    0.82
    odore
    0.82
    tenance
    0.80
    resa
    0.77
    bnb
    0.76
    withstanding
    0.75
    ashtra
    0.73
    xiety
    0.70
    ogether
    0.69
    Act Density 0.247%

    No Known Activations