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

    Neuronpedia

    INDEX
    Explanations

    elements related to authority and power structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.57
    RetentionPolicy
    -0.56
    SBATCH
    -0.53
    GOTREF
    -0.52
    ViewFeatures
    -0.52
    kels
    -0.51
    softc
    -0.50
     Compens
    -0.47
    eip
    -0.46
    typeorm
    -0.46
    POSITIVE LOGITS
     feasting
    0.66
     виправивши
    0.55
    Numerous
    0.54
     Numerade
    0.53
     everywhere
    0.53
     rampant
    0.53
     peer
    0.52
     prosperity
    0.52
     prosperous
    0.52
    everywhere
    0.51
    Act Density 0.104%

    No Known Activations