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

    Neuronpedia

    INDEX
    Explanations

    references to significant historical events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.94
    Downloadha
    -0.93
    Flow
    -0.84
    gans
    -0.77
    ernels
    -0.76
    Kids
    -0.76
    cham
    -0.74
    xia
    -0.73
    conom
    -0.72
    vier
    -0.72
    POSITIVE LOGITS
     preservation
    1.10
     lows
    1.01
     landmark
    1.01
     significance
    0.97
    istically
    0.94
     achievement
    0.85
     highs
    0.84
    orically
    0.82
    ised
    0.80
     proportions
    0.80
    Act Density 0.009%

    No Known Activations