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

    Neuronpedia

    INDEX
    Explanations

    terms related to membership or affiliation with various organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to membership in various organizations or official roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depiction
    -0.73
    etheus
    -0.71
    merce
    -0.68
     stink
    -0.66
     preval
    -0.66
     candles
    -0.66
     grate
    -0.66
     roar
    -0.66
     sucker
    -0.65
     engulf
    -0.64
    POSITIVE LOGITS
     parliament
    0.83
     Parliament
    0.83
     Nanto
    0.80
     Administ
    0.75
    odox
    0.72
     Upper
    0.70
    zai
    0.69
    Boost
    0.67
     Highlands
    0.67
     Optional
    0.67
    Act Density 0.095%

    No Known Activations