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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of being a proxy for something else

    oai_token-act-pair · gpt-3.5-turbo

    references to "proxy" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynski
    -0.93
    alos
    -0.84
    ardy
    -0.83
    ership
    -0.81
    nen
    -0.80
    ivism
    -0.80
    ews
    -0.79
    ymes
    -0.79
    ŃĶ
    -0.78
    opathy
    -0.76
    POSITIVE LOGITS
     proxy
    0.95
     proxies
    0.83
     Tempest
    0.79
     wars
    0.71
     landsl
    0.70
     sibling
    0.69
     warfare
    0.67
     versa
    0.65
     aggression
    0.65
     flare
    0.64
    Act Density 0.027%

    No Known Activations