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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and integrals related to functions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blackburn
    -0.15
    ritt
    -0.15
    lparr
    -0.15
    Dog
    -0.15
     Dog
    -0.15
    acen
    -0.14
    uš
    -0.14
    stice
    -0.14
     Dogs
    -0.14
     Dude
    -0.14
    POSITIVE LOGITS
     dx
    0.38
     dt
    0.36
    dt
    0.36
    dx
    0.35
     dy
    0.33
     ds
    0.31
     dz
    0.30
     du
    0.30
     DX
    0.27
    .dt
    0.27
    Act Density 0.090%

    No Known Activations