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

    Neuronpedia

    INDEX
    Explanations

    cities and locations

    oai_token-act-pair · gpt-3.5-turbo

    names of specific geographical locations and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ageing
    -0.87
     favourites
    -0.81
     Fifa
    -0.77
     defences
    -0.73
     realised
    -0.71
     realise
    -0.70
     organis
    -0.67
     organisers
    -0.66
    )=(
    -0.65
     colour
    -0.65
    POSITIVE LOGITS
    acus
    0.77
    asca
    0.74
    esque
    0.72
     honors
    0.71
    Brook
    0.69
     alum
    0.67
    icum
    0.66
    Boston
    0.66
    ola
    0.65
    vale
    0.65
    Act Density 0.627%

    No Known Activations