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

    Neuronpedia

    INDEX
    Explanations

    phrases related to institutional aspects or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to institutional concepts or structures, particularly in relation to social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.90
    spell
    -0.81
    vich
    -0.80
    bane
    -0.79
    ï¸ı
    -0.78
    kers
    -0.78
    nen
    -0.77
    word
    -0.76
    words
    -0.74
    manship
    -0.73
    POSITIVE LOGITS
    ized
    1.37
    ization
    1.20
    ised
    1.18
    izes
    1.08
    itutional
    1.05
    izing
    1.01
    izations
    1.00
    izational
    0.98
    isation
    0.98
    ize
    0.97
    Act Density 0.021%

    No Known Activations