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

    Neuronpedia

    INDEX
    Explanations

    quantitative values such as numbers or percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or categories of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bombs
    -0.67
    leep
    -0.65
     tun
    -0.61
     assum
    -0.60
    lest
    -0.59
     researching
    -0.59
     forget
    -0.58
    uning
    -0.57
     digging
    -0.57
     undet
    -0.57
    POSITIVE LOGITS
     pinnacle
    0.76
    ICAN
    0.70
    OPLE
    0.69
    hematic
    0.69
     XY
    0.68
     constituents
    0.68
     culmination
    0.67
     entirety
    0.66
    opian
    0.65
    wark
    0.64
    Act Density 0.151%

    No Known Activations