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

    Neuronpedia

    INDEX
    Explanations

    names or terms ending in 'uca', 'ña', or 'ema'

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to people or places, particularly those with Spanish origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sheet
    -0.80
    sonian
    -0.78
    balance
    -0.73
    matically
    -0.73
    drawn
    -0.71
    writers
    -0.70
    ensible
    -0.70
     glim
    -0.70
    yright
    -0.70
     unaff
    -0.69
    POSITIVE LOGITS
    ñ
    1.06
    ÅĤ
    1.01
    ÅŁ
    1.00
    issance
    0.98
    qua
    0.97
    zza
    0.93
    ÄŁ
    0.92
    ibo
    0.91
    UGH
    0.90
    velength
    0.90
    Act Density 0.085%

    No Known Activations