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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict or competition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confrontations or competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocument
    -0.72
    nothing
    -0.71
    birth
    -0.71
    serving
    -0.69
    gement
    -0.65
    hood
    -0.65
    ascript
    -0.64
    redo
    -0.63
    Chart
    -0.63
    adequ
    -0.62
    POSITIVE LOGITS
     opponents
    0.95
     opponent
    0.93
     against
    0.92
     finalists
    0.92
     rivals
    0.89
     fellow
    0.87
     challengers
    0.83
     competitors
    0.81
     adversaries
    0.80
     rival
    0.79
    Act Density 0.161%

    No Known Activations