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

    Neuronpedia

    INDEX
    Explanations

    references to social structures, classes, and systems within political and economic contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to social structures and relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.85
    gger
    -0.76
    wered
    -0.72
     Cursed
    -0.72
    xual
    -0.70
    nant
    -0.70
    ï¸ı
    -0.68
     Lank
    -0.66
    ñ
    -0.66
    xus
    -0.63
    POSITIVE LOGITS
     norms
    0.85
     relations
    0.84
     welfare
    0.79
     democr
    0.78
    ized
    0.77
     cohesion
    0.74
     federation
    0.73
     amenities
    0.72
    istic
    0.72
     hygiene
    0.71
    Act Density 0.026%

    No Known Activations