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

    Neuronpedia

    INDEX
    Explanations

    references to thresholds and concepts of transparency in data or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.68
      
    -0.60
     best
    -0.59
     l
    -0.57
     send
    -0.57
    i
    -0.57
     last
    -0.55
     rest
    -0.55
     L
    -0.55
    ori
    -0.54
    POSITIVE LOGITS
     snippetHide
    1.09
     myſelf
    1.08
     Efq
    1.05
    Personensuche
    1.03
    NUMX
    1.02
     contextLoads
    1.01
    UnusedPrivate
    1.00
     auffi
    0.99
     ſche
    0.98
     mitigate
    0.96
    Act Density 0.103%

    No Known Activations