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

    Neuronpedia

    INDEX
    Explanations

    names related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to hierarchical business structures or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rated
    -1.09
    req
    -0.65
     razor
    -0.65
    ŃĶ
    -0.64
     bald
    -0.63
     dement
    -0.63
     Noct
    -0.62
    Reviewer
    -0.61
    DEM
    -0.61
     HOUSE
    -0.60
    POSITIVE LOGITS
    vous
    1.04
    le
    0.93
    lean
    0.91
    witz
    0.89
    bach
    0.89
    iday
    0.87
    theless
    0.86
    ieu
    0.85
    chel
    0.84
    wagon
    0.84
    Act Density 0.012%

    No Known Activations