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

    Neuronpedia

    INDEX
    Explanations

    words related to negotiations, plans, concerns, and arrangements

    oai_token-act-pair · gpt-3.5-turbo

    words related to uncertainty or hope in contexts of discussion and negotiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DA
    -0.67
     Wonders
    -0.63
    ovie
    -0.62
     olds
    -0.61
    endment
    -0.60
    purpose
    -0.60
     Sod
    -0.59
    Adds
    -0.58
     Depression
    -0.58
    Cos
    -0.57
    POSITIVE LOGITS
     ensued
    0.95
     arose
    0.88
     flowed
    0.84
     prevailed
    0.81
     resumed
    0.79
     sprang
    0.76
     emerged
    0.74
     arises
    0.74
     surged
    0.73
     crept
    0.73
    Act Density 0.363%

    No Known Activations