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

    Neuronpedia

    INDEX
    Explanations

    physical objects or concepts related to various fields and domains

    oai_token-act-pair · gpt-3.5-turbo

    nouns and specific objects related to various contexts and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berra
    -0.61
    NetMessage
    -0.60
     Flavoring
    -0.60
    laus
    -0.56
    Redd
    -0.54
     Magicka
    -0.53
     Residential
    -0.53
    vironment
    -0.51
    llular
    -0.50
    lihood
    -0.50
    POSITIVE LOGITS
     cutter
    0.68
    wright
    0.63
    washer
    0.62
    wife
    0.61
    folio
    0.61
     regiment
    0.61
    fighter
    0.61
    maker
    0.60
     rul
    0.60
     maker
    0.60
    Act Density 0.748%

    No Known Activations