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

    Neuronpedia

    INDEX
    Explanations

    references to things that are unusual or unconventional

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Against
    -0.66
     Workshop
    -0.63
     Painting
    -0.63
     tailor
    -0.62
    Close
    -0.62
    acist
    -0.61
    orah
    -0.59
     towed
    -0.59
    andan
    -0.58
     Another
    -0.58
    POSITIVE LOGITS
    ball
    0.72
    iversary
    0.69
    bj
    0.68
    eah
    0.68
    balls
    0.66
    amount
    0.65
     omission
    0.64
    ities
    0.63
     acron
    0.63
     distribut
    0.62
    Act Density 0.120%

    No Known Activations