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

    Neuronpedia

    INDEX
    Explanations

    strings containing variable assignments or mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    mathematical terms and concepts related to probabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grassroots
    -0.90
     overseen
    -0.84
     whistlebl
    -0.81
     vetted
    -0.80
    Privacy
    -0.77
     vetting
    -0.76
     spearheaded
    -0.76
     secretive
    -0.75
    license
    -0.75
     nonprofits
    -0.74
    POSITIVE LOGITS
     theorem
    1.22
     \(
    1.21
     \(\
    1.20
     algebra
    1.15
     $\
    1.12
     interpol
    1.11
     Mathemat
    1.09
    orem
    1.08
     equilibrium
    1.06
     ÎĶ
    1.05
    Act Density 0.754%

    No Known Activations