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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing qualities or states with a strong impact or importance

    oai_token-act-pair · gpt-3.5-turbo

    words that convey significance or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RPG
    -0.61
    udeb
    -0.60
    ioxide
    -0.58
    aminer
    -0.57
     Battlefield
    -0.55
    Definition
    -0.55
    ihadi
    -0.54
    endment
    -0.54
    iphate
    -0.54
     Pledge
    -0.53
    POSITIVE LOGITS
    etheless
    1.06
    ortunately
    0.84
     observers
    0.74
    ly
    0.73
     enough
    0.72
    nesses
    0.72
     ones
    0.69
     alike
    0.68
     amounts
    0.67
    =]
    0.67
    Act Density 0.604%

    No Known Activations