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

    Neuronpedia

    INDEX
    Explanations

    words related to national contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to national identities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.85
    herty
    -0.82
    ullivan
    -0.73
     Coffin
    -0.70
    furt
    -0.69
    OHN
    -0.68
     Twain
    -0.66
    enhagen
    -0.63
     Stanton
    -0.63
    eva
    -0.63
    POSITIVE LOGITS
    ised
    1.17
    istic
    1.17
    ities
    1.12
    isms
    1.07
    isations
    1.04
    isation
    1.01
     Geographic
    0.99
    ized
    0.99
    istically
    0.94
    ization
    0.94
    Act Density 0.043%

    No Known Activations