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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or aliases of public figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms that indicate alternative names or aliases for individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.70
    stad
    -0.69
    Impl
    -0.68
    pson
    -0.66
    ÃŃs
    -0.64
    urrent
    -0.63
    hani
    -0.62
    avorable
    -0.62
    Topics
    -0.62
    onel
    -0.62
    POSITIVE LOGITS
     CoC
    0.78
     HERO
    0.75
     Chosen
    0.74
     yours
    0.70
     "@
    0.67
     Boss
    0.67
     æ
    0.65
     oxy
    0.64
     "#
    0.64
     è£ıè
    0.62
    Act Density 0.015%

    No Known Activations