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

    Neuronpedia

    INDEX
    Explanations

    keywords related to criminal activities, particularly murder

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "murder."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zl
    -0.77
    Stud
    -0.71
    english
    -0.68
    Scot
    -0.68
    arta
    -0.66
    UTC
    -0.66
     reusable
    -0.65
    une
    -0.64
    DIR
    -0.64
    Cola
    -0.64
    POSITIVE LOGITS
     murder
    1.15
     spree
    1.08
     murders
    1.05
     homicide
    1.04
     Murder
    0.97
     homicides
    0.95
    hyde
    0.93
     murderer
    0.92
     manslaughter
    0.92
     killings
    0.90
    Act Density 0.014%

    No Known Activations