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

    Neuronpedia

    INDEX
    Explanations

    mentions of support for various causes or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to political or social backing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sweat
    -0.67
     Rim
    -0.64
    ModLoader
    -0.62
    Ir
    -0.60
     Reeves
    -0.59
    selves
    -0.58
     unbeliev
    -0.58
     Hebdo
    -0.58
    neys
    -0.58
     burg
    -0.58
    POSITIVE LOGITS
    itism
    0.97
    Support
    0.82
    arity
    0.80
    ability
    0.79
     Supports
    0.74
    leader
    0.74
    ãĥĨ
    0.73
    asio
    0.72
    byn
    0.72
    ative
    0.71
    Act Density 0.052%

    No Known Activations