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

    Neuronpedia

    INDEX
    Explanations

    pronouns, conjunctions, and prepositions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal entities or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Category
    -0.69
    Template
    -0.64
    ayson
    -0.63
     Seym
    -0.63
    cture
    -0.61
    æ©
    -0.60
    erenn
    -0.58
     Moroc
    -0.57
    agra
    -0.55
    Daddy
    -0.54
    POSITIVE LOGITS
    zbollah
    0.64
     alike
    0.63
     thereof
    0.58
     consequ
    0.57
    htm
    0.57
    osponsors
    0.56
     thereafter
    0.55
    _>
    0.55
    \":
    0.55
     Reincarnated
    0.54
    Act Density 0.184%

    No Known Activations