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

    Neuronpedia

    INDEX
    Explanations

    references to directors and leadership roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ***!
    -0.59
    TagMode
    -0.57
    الحياه
    -0.57
    CodeAttribute
    -0.56
    neval
    -0.55
    bital
    -0.55
    enos
    -0.55
     sahi
    -0.54
    kst
    -0.52
    ensement
    -0.52
    POSITIVE LOGITS
    directors
    0.52
    pakking
    0.47
     Nothing
    0.46
     director
    0.46
     click
    0.45
    director
    0.45
     nothing
    0.43
     nemlig
    0.43
     diretor
    0.43
     LoggerFactory
    0.42
    Act Density 0.370%

    No Known Activations