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

    Neuronpedia

    INDEX
    Explanations

    mentions of institutional settings or practices

    oai_token-act-pair · gpt-3.5-turbo

    references to institutional concepts or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.91
    bane
    -0.77
    nen
    -0.77
    ky
    -0.76
    hner
    -0.75
    ragon
    -0.75
    spell
    -0.75
    kers
    -0.75
    vich
    -0.74
    word
    -0.73
    POSITIVE LOGITS
    ized
    1.29
    ization
    1.21
    ised
    1.10
    itutional
    1.08
    izes
    1.01
    izational
    0.98
    isation
    0.98
    izing
    0.97
    izations
    0.96
     institutions
    0.96
    Act Density 0.015%

    No Known Activations