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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     previously
    -0.18
    ë§IJ
    -0.17
     recently
    -0.15
     ìļ°ë¦¬ëĬĶ
    -0.15
     Possibly
    -0.14
    .EventQueue
    -0.14
    etc
    -0.14
    ly
    -0.14
    ãģĦ
    -0.14
    ãģ£ãģ¨
    -0.14
    POSITIVE LOGITS
    /w
    0.40
    nt
    0.34
    otope
    0.33
     hereby
    0.29
     indeed
    0.28
    /is
    0.27
     gonna
    0.26
    olation
    0.25
     not
    0.24
    rael
    0.24
    Act Density 1.430%

    No Known Activations