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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or associations between events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stall
    -0.95
    ipel
    -0.83
    oiler
    -0.82
     Fernand
    -0.76
     ãĤµ
    -0.73
    inse
    -0.72
    jew
    -0.72
     Splash
    -0.69
    uck
    -0.67
    !/
    -0.67
    POSITIVE LOGITS
     dealings
    0.87
     negotiations
    0.85
     cases
    0.81
     thereto
    0.77
     instances
    0.77
     transactions
    0.74
    essions
    0.73
     robberies
    0.73
     payments
    0.72
     proceedings
    0.72
    Act Density 0.013%

    No Known Activations