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

    Neuronpedia

    INDEX
    Explanations

    references to brevity and concise content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quite
    -0.20
    agal
    -0.17
    lesi
    -0.16
    æĮº
    -0.16
     pretty
    -0.15
    quite
    -0.15
     Quite
    -0.15
     fairly
    -0.15
    XD
    -0.14
    orian
    -0.14
    POSITIVE LOGITS
    -basic
    0.26
     basic
    0.26
    basic
    0.26
    /basic
    0.25
     brief
    0.24
     briefly
    0.23
     basics
    0.23
    brief
    0.22
     Brief
    0.22
     Basic
    0.21
    Act Density 0.009%

    No Known Activations