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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific person

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Joe Biden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jian
    -0.72
    afia
    -0.70
    icles
    -0.70
    istors
    -0.68
    onz
    -0.68
     Mara
    -0.68
    ience
    -0.66
    eal
    -0.66
    ouston
    -0.64
    ramid
    -0.63
    POSITIVE LOGITS
    geon
    0.97
     Biden
    0.88
    vier
    0.84
    ught
    0.80
    keeper
    0.78
    ocamp
    0.75
    LECT
    0.74
    cloth
    0.73
    geons
    0.73
    osc
    0.71
    Act Density 0.115%

    No Known Activations