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

    Neuronpedia

    INDEX
    Explanations

    Spanish or Latin terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    elements related to the concept of surrender or capture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accountability
    -0.67
     Pwr
    -0.63
     Parish
    -0.58
     Lines
    -0.56
     Own
    -0.54
     Balanced
    -0.54
     Integrity
    -0.52
     Cheong
    -0.52
     Tracker
    -0.52
     Transparency
    -0.51
    POSITIVE LOGITS
    iped
    0.57
    arious
    0.57
    id
    0.57
    kered
    0.57
    ule
    0.56
    icultural
    0.56
    oots
    0.56
    omorph
    0.56
    ores
    0.56
    ote
    0.56
    Act Density 0.427%

    No Known Activations