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

    Neuronpedia

    INDEX
    Explanations

    words related to political or military intervention

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intervention in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cale
    -0.72
    WE
    -0.70
    models
    -0.69
    λ
    -0.68
     Boh
    -0.66
     Bones
    -0.65
    carbon
    -0.64
    Export
    -0.64
    house
    -0.63
    ndra
    -0.63
    POSITIVE LOGITS
    ateral
    1.07
     intervene
    0.90
    anke
    0.89
     interven
    0.88
    aries
    0.87
     intervention
    0.87
    ulatory
    0.85
     intervened
    0.77
    arie
    0.76
     intervening
    0.74
    Act Density 0.033%

    No Known Activations