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

    Neuronpedia

    INDEX
    Explanations

    descriptions of individuals using specific terms to define themselves

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing self-identification or self-description labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isons
    -0.79
    ubi
    -0.73
    anqu
    -0.71
    adata
    -0.71
    azaki
    -0.70
    anches
    -0.67
    akings
    -0.66
    itations
    -0.64
     vibrations
    -0.63
    elight
    -0.62
    POSITIVE LOGITS
    sty
    0.90
     member
    0.81
     believer
    0.80
     adherent
    0.80
     newcomer
    0.77
     legislator
    0.76
     former
    0.75
     resident
    0.73
     founder
    0.71
     gunman
    0.71
    Act Density 0.082%

    No Known Activations