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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improvement and cooperation in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to balance and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     looph
    -0.67
     battered
    -0.60
    stall
    -0.58
     condem
    -0.56
     arra
    -0.54
    apego
    -0.52
     sworn
    -0.52
     accuses
    -0.51
     foul
    -0.51
     blot
    -0.50
    POSITIVE LOGITS
     accordingly
    1.05
     instead
    1.00
    instead
    1.00
     easier
    1.00
     quicker
    0.95
     respectively
    0.94
    rather
    0.93
     smoother
    0.91
     alike
    0.91
     :)
    0.90
    Act Density 0.736%

    No Known Activations