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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political structures and divisions of power

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of separation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arcity
    -0.75
    Demand
    -0.69
    idon
    -0.68
     sustained
    -0.67
    demand
    -0.65
    uti
    -0.64
     nud
    -0.63
     tremend
    -0.58
    nor
    -0.58
     breakthrough
    -0.57
    POSITIVE LOGITS
     sexes
    0.84
    ombat
    0.79
     thirds
    0.73
    isions
    0.70
    owship
    0.69
     geographically
    0.68
     evenly
    0.68
    inational
    0.68
     halves
    0.68
    iple
    0.67
    Act Density 0.234%

    No Known Activations