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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or places with the term "Faire" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'fair'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odd
    -0.67
    ologically
    -0.67
    insula
    -0.66
     arresting
    -0.65
    igating
    -0.65
    umm
    -0.63
    uzzle
    -0.63
    ulates
    -0.62
    igsaw
    -0.61
    ushed
    -0.60
    POSITIVE LOGITS
    aire
    1.27
     Lys
    0.80
     Francois
    0.79
    neau
    0.79
    nat
    0.79
    eers
    0.75
    aires
    0.74
     François
    0.73
     Leban
    0.73
    ppe
    0.73
    Act Density 0.007%

    No Known Activations