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

    Neuronpedia

    INDEX
    Explanations

    names starting with "Nicho" or "Pont" and similar commonly paired words

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals named Nicholas and Pont

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ministic
    -0.80
    lance
    -0.77
    earing
    -0.74
    ª
    -0.74
    ITNESS
    -0.73
    istani
    -0.72
    abil
    -0.72
    ctors
    -0.70
    qua
    -0.67
    ited
    -0.67
    POSITIVE LOGITS
    olas
    1.14
    sis
    0.82
    inez
    0.75
    frey
    0.72
    umber
    0.72
     Cage
    0.71
     Coliseum
    0.69
     Barcl
    0.68
    ols
    0.66
    olls
    0.65
    Act Density 0.071%

    No Known Activations