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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, often related to people or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of proper nouns and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.70
     hostages
    -0.69
     tremend
    -0.69
    ²¾
    -0.69
    ģ«
    -0.67
     hindsight
    -0.65
     Skydragon
    -0.62
     captivity
    -0.61
     impulse
    -0.60
    ¿½
    -0.60
    POSITIVE LOGITS
    akeru
    0.88
    ihu
    0.80
    rescent
    0.71
    dale
    0.68
    erella
    0.68
    ounter
    0.68
    aste
    0.67
    eret
    0.66
     Nieto
    0.66
    utor
    0.66
    Act Density 0.118%

    No Known Activations