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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    references to "the" and its frequency in phrases indicating specific contexts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illes
    -0.82
    isson
    -0.78
    illon
    -0.67
    aur
    -0.66
    ioned
    -0.65
    itia
    -0.64
    claimer
    -0.64
    vet
    -0.64
    Ops
    -0.64
    ovo
    -0.63
    POSITIVE LOGITS
     sake
    1.36
     foreseeable
    1.04
     purposes
    1.00
     fledgling
    0.97
     sexes
    0.90
     remainder
    0.85
     occupants
    0.84
     entire
    0.84
     rest
    0.82
     reasons
    0.82
    Act Density 0.255%

    No Known Activations