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

    Neuronpedia

    INDEX
    Explanations

    structured data formats or components in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.62
     "
    -0.55
     I
    -0.54
     J
    -0.54
     g
    -0.54
     k
    -0.53
     [
    -0.53
     kon
    -0.53
    till
    -0.51
     a
    -0.51
    POSITIVE LOGITS
    \{\\
    1.14
    tagHelperRunner
    1.12
    ſelf
    1.10
    ſelves
    1.09
    ScopeManager
    1.05
     Majefty
    1.04
     متعلقه
    1.03
     iſt
    1.03
     Anſ
    1.00
    SPJ
    0.96
    Act Density 0.003%

    No Known Activations