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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical thresholds or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanto
    -0.78
     sake
    -0.76
     Chronicle
    -0.63
     descended
    -0.63
     Tec
    -0.63
     Kens
    -0.62
     parted
    -0.57
     arose
    -0.57
     shalt
    -0.57
     distinguished
    -0.57
    POSITIVE LOGITS
    levels
    0.91
     milestones
    0.86
     milestone
    0.85
     heights
    0.84
    reshold
    0.78
     hurdle
    0.77
    strate
    0.76
    LOD
    0.76
    chwitz
    0.75
     levels
    0.74
    Act Density 0.266%

    No Known Activations