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

    Neuronpedia

    INDEX
    Explanations

    mentions of institutional concepts or practices

    oai_token-act-pair · gpt-3.5-turbo

    references to institutional frameworks or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.83
    hner
    -0.80
    yah
    -0.77
    bane
    -0.77
    kers
    -0.76
    nen
    -0.76
    ï¸ı
    -0.73
    gets
    -0.73
    spell
    -0.73
    ky
    -0.71
    POSITIVE LOGITS
    ized
    1.29
    ization
    1.14
    ised
    1.12
    itutional
    1.11
    izes
    1.02
     affili
    1.00
    izational
    1.00
    izations
    0.99
    isation
    0.98
     institutions
    0.96
    Act Density 0.008%

    No Known Activations