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

    Neuronpedia

    INDEX
    Explanations

    mentions of cultural activities, events, and expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to culture and its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.92
    wered
    -0.78
    fman
    -0.74
    elfth
    -0.73
    issan
    -0.68
    enary
    -0.68
    igible
    -0.67
    apor
    -0.67
    eenth
    -0.66
    igans
    -0.66
    POSITIVE LOGITS
     clash
    1.01
     wars
    0.97
     appropriation
    0.91
     shock
    0.89
     immersion
    0.83
     clashes
    0.83
     indo
    0.83
     norms
    0.82
    artifacts
    0.80
     Marxism
    0.76
    Act Density 0.062%

    No Known Activations