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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles of individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regor
    -0.76
     Defin
    -0.66
    bernatorial
    -0.65
    acters
    -0.65
    sylv
    -0.61
     snag
    -0.60
    ython
    -0.60
    ividual
    -0.60
     thrilling
    -0.60
     retrieving
    -0.59
    POSITIVE LOGITS
     è£ıè
    0.72
    ouri
    0.69
     Greenwood
    0.68
    ãĥ³ãĤ¸
    0.65
     Form
    0.65
     Abe
    0.64
     Mahmoud
    0.63
     Abd
    0.63
     Pres
    0.62
     Owens
    0.62
    Act Density 0.366%

    No Known Activations