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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government actions and interventions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government and political activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achu
    -0.61
     recomb
    -0.56
    ouple
    -0.55
    Spoiler
    -0.55
    uple
    -0.55
     Pirate
    -0.54
    Chain
    -0.52
     Fur
    -0.52
    oret
    -0.52
    CLUD
    -0.52
    POSITIVE LOGITS
    reach
    0.75
     abroad
    0.67
    outs
    0.67
    tracks
    0.66
    warts
    0.66
    vertisements
    0.66
    insky
    0.66
    iets
    0.64
    ĸļ
    0.64
    iness
    0.63
    Act Density 0.552%

    No Known Activations