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

    Neuronpedia

    INDEX
    Explanations

    locations or place names, specifically ones ending in "der" and "der"

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or groups, particularly in a context of comparison or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ured
    -0.69
     reprodu
    -0.65
    urious
    -0.63
     filib
    -0.62
    urers
    -0.61
     crim
    -0.60
     veter
    -0.58
     Mehran
    -0.57
     showc
    -0.57
    rosse
    -0.55
    POSITIVE LOGITS
    theless
    1.31
    dash
    1.25
    mere
    1.14
    bolt
    1.06
    wise
    0.99
    lust
    0.99
    dale
    0.95
    mia
    0.95
    side
    0.95
    pool
    0.95
    Act Density 0.086%

    No Known Activations