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

    Neuronpedia

    INDEX
    Explanations

    references to missing persons, particularly in relation to the circumstances surrounding their disappearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.64
     Vikipedi
    -0.63
    newtheorem
    -0.60
    ogno
    -0.54
    liegt
    -0.54
     WebApplication
    -0.53
    ematic
    -0.53
     AGO
    -0.53
    wikidata
    -0.53
    enderror
    -0.53
    POSITIVE LOGITS
     safety
    0.74
    safety
    0.68
     Safety
    0.67
    Safety
    0.62
     SAFETY
    0.59
     missing
    0.58
    WaitGroup
    0.57
     Missing
    0.55
     rescue
    0.52
    Missing
    0.51
    Act Density 0.189%

    No Known Activations