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

    Neuronpedia

    INDEX
    Explanations

    words related to legal matters and crime

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "crime."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.71
     Franç
    -0.65
     Schumer
    -0.65
     Mandela
    -0.61
     Dems
    -0.58
     Niger
    -0.58
     quo
    -0.57
    lement
    -0.57
     Haley
    -0.56
     Ãľ
    -0.56
    POSITIVE LOGITS
    aldi
    1.18
    inals
    1.17
    onial
    1.12
    shaw
    1.11
    ming
    1.10
    inally
    1.06
    mage
    1.01
    inatory
    0.99
    mie
    0.96
    etric
    0.95
    Act Density 0.034%

    No Known Activations