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

    Neuronpedia

    INDEX
    Explanations

    references to investigations or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ấu
    -0.18
    atre
    -0.15
    ERO
    -0.15
    anga
    -0.15
    ming
    -0.14
     close
    -0.14
    atab
    -0.14
    acob
    -0.14
    ĽĪ
    -0.13
    eric
    -0.13
    POSITIVE LOGITS
    LOSS
    0.15
    ylon
    0.15
    ÑĤиÑı
    0.14
    .ImageAlign
    0.14
    .Transactional
    0.14
    exo
    0.14
    oring
    0.14
    bett
    0.14
    hog
    0.14
    hoot
    0.14
    Act Density 0.004%

    No Known Activations