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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific location or person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.82
    ship
    -0.70
    tainment
    -0.67
    tions
    -0.66
     Appropriations
    -0.66
    ATOR
    -0.66
    yrinth
    -0.65
     McCann
    -0.65
    sburgh
    -0.63
    LECT
    -0.62
    POSITIVE LOGITS
     Sha
    1.26
    ikh
    0.89
     Tsu
    0.87
    olin
    0.87
    isha
    0.86
    osh
    0.85
    ivas
    0.85
    ulk
    0.84
     Yao
    0.79
    jah
    0.77
    Act Density 0.007%

    No Known Activations