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

    Neuronpedia

    INDEX
    Explanations

    phrases related to searching or discovering, especially with a focus on history or records

    oai_token-act-pair · gpt-3.5-turbo

    words that convey strong emotional or dramatic narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sport
    -0.77
     Kun
    -0.75
     Canter
    -0.74
     Cors
    -0.71
     Kessler
    -0.67
    ij士
    -0.66
     NEO
    -0.66
     LTD
    -0.64
     Swan
    -0.63
     Sek
    -0.61
    POSITIVE LOGITS
    reci
    0.82
    andestine
    0.75
    mage
    0.70
    aunders
    0.70
    lain
    0.69
    ivable
    0.69
    omes
    0.66
    idious
    0.65
    ofi
    0.65
    eatured
    0.63
    Act Density 0.000%

    No Known Activations