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

    Neuronpedia

    INDEX
    Explanations

    references to military statistics and crime-related data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ering
    -0.14
    ritic
    -0.14
    aval
    -0.14
    obel
    -0.14
     Lady
    -0.14
    fmt
    -0.14
    URITY
    -0.13
    积
    -0.13
     sensit
    -0.13
     phenomen
    -0.13
    POSITIVE LOGITS
     unintention
    0.21
    tainment
    0.18
     motor
    0.17
    entai
    0.17
     homicides
    0.17
    Coding
    0.17
     Injury
    0.16
     Coding
    0.16
     fat
    0.16
     intimate
    0.15
    Act Density 0.036%

    No Known Activations