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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and performance characteristics of vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γμα
    -0.16
    VOKE
    -0.15
    oga
    -0.15
    çĸ
    -0.15
    á»Ŀ
    -0.15
    ervice
    -0.14
    ingen
    -0.13
    νÏī
    -0.13
     ifndef
    -0.13
     Replacement
    -0.13
    POSITIVE LOGITS
     Stability
    0.25
     stability
    0.24
     Corner
    0.21
     instability
    0.21
     balance
    0.20
     Balance
    0.20
     corner
    0.18
     controls
    0.18
    Balance
    0.17
     control
    0.17
    Act Density 0.075%

    No Known Activations