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

    Neuronpedia

    INDEX
    Explanations

    references to research and learning methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.57
    点此举报
    -0.53
    /**
    -0.50
     OMITBAD
    -0.49
    writeFieldEnd
    -0.48
     MainAxisSize
    -0.47
    KommentareTeilen
    -0.45
     defaultstate
    -0.45
    exitRule
    -0.44
    \{\\
    -0.43
    POSITIVE LOGITS
     googling
    1.87
     researching
    1.82
     google
    1.78
     research
    1.77
     Google
    1.72
     googled
    1.63
     researched
    1.61
    research
    1.60
    Google
    1.53
     GOOGLE
    1.48
    Act Density 0.788%

    No Known Activations