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

    Neuronpedia

    INDEX
    Explanations

    locations within a specific town named "Nueva Italia"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.90
    aceutical
    -0.72
    acl
    -0.69
    icum
    -0.68
    Agg
    -0.67
    intosh
    -0.66
    arna
    -0.66
    olid
    -0.64
    eligible
    -0.64
    ingham
    -0.64
    POSITIVE LOGITS
    lla
    1.24
    llo
    1.05
    lling
    0.99
    lly
    0.97
    lled
    0.96
    hler
    0.96
    llers
    0.92
    ll
    0.91
    pees
    0.90
    hner
    0.88
    Act Density 0.030%

    No Known Activations