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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons of different entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    jo
    -0.77
    BIL
    -0.76
    oma
    -0.72
    asma
    -0.66
    vet
    -0.63
    cca
    -0.63
     unilaterally
    -0.63
    ARA
    -0.63
    omas
    -0.62
     nonetheless
    -0.62
    POSITIVE LOGITS
     world
    1.11
     country
    1.01
     globe
    0.96
     spectrum
    0.94
     alphabet
    0.89
     nation
    0.82
     populace
    0.81
     continent
    0.79
     kingdom
    0.77
     remainder
    0.77
    Act Density 0.047%

    No Known Activations