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

    Neuronpedia

    INDEX
    Explanations

    mentions of places and their association with different entities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "home to" followed by various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.82
    hiba
    -0.81
    iol
    -0.72
    iev
    -0.69
    é¾
    -0.69
    ongyang
    -0.68
     direction
    -0.68
     cooker
    -0.68
     warrants
    -0.67
    proxy
    -0.66
    POSITIVE LOGITS
     plenty
    0.73
     Goose
    0.72
     Newt
    0.70
     trillions
    0.68
    enstein
    0.66
     attractions
    0.65
     dozens
    0.64
     lavish
    0.63
     brood
    0.62
     lots
    0.62
    Act Density 0.061%

    No Known Activations