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

    Neuronpedia

    INDEX
    Explanations

    groups or collections of entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe groups or coalitions composed of multiple entities or members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estamp
    -0.74
    bringer
    -0.73
     stride
    -0.71
    pal
    -0.67
    runtime
    -0.66
    eway
    -0.65
    oway
    -0.65
     Judgment
    -0.63
    acing
    -0.62
    elsius
    -0.62
    POSITIVE LOGITS
     disparate
    0.90
     finalists
    0.89
     stakeholders
    0.89
     collaborators
    0.88
     partners
    0.86
     factions
    0.86
     siblings
    0.80
     nations
    0.80
     predecessors
    0.79
     acron
    0.78
    Act Density 0.296%

    No Known Activations