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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and constructs in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amazing
    -0.77
     awesome
    -0.67
     wonderful
    -0.66
     beautiful
    -0.60
    期刊论文
    -0.59
     +/-
    -0.59
     concepts
    -0.57
    beli
    -0.57
    epi
    -0.56
    abha
    -0.56
    POSITIVE LOGITS
    hasMoreElements
    0.67
     reportedly
    0.66
    ThroughAttribute
    0.66
    enderror
    0.66
    elemField
    0.64
    Meanwhile
    0.63
    ToListAsync
    0.62
     }{@
    0.61
     lenker
    0.61
     blamed
    0.61
    Act Density 0.286%

    No Known Activations