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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to a specific location ("ille") that could be a city or person's name

    oai_token-act-pair · gpt-3.5-turbo

    locations or names associated with 'ville.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.81
    -+-+
    -0.76
    icum
    -0.76
    reme
    -0.71
    arrell
    -0.71
     DPR
    -0.70
    etheless
    -0.70
    eanor
    -0.69
    iates
    -0.68
    iating
    -0.68
    POSITIVE LOGITS
    tto
    1.33
    ttes
    1.15
    tt
    1.12
    hammer
    1.04
    tta
    1.00
    lla
    0.98
    tti
    0.95
    brand
    0.95
    mma
    0.93
    phant
    0.90
    Act Density 0.044%

    No Known Activations