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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference negative consequences or actions attributed to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugal
    -0.17
    èĬ³
    -0.15
    contres
    -0.15
    .scalablytyped
    -0.14
    ÑĢиÑĦ
    -0.14
    dÄĽ
    -0.14
    [".
    -0.14
    imentary
    -0.14
    osg
    -0.13
    atik
    -0.13
    POSITIVE LOGITS
    ler
    0.17
     yet
    0.15
     with
    0.15
     Inbox
    0.15
     nothing
    0.14
    ailer
    0.14
    sett
    0.14
     worth
    0.14
    xx
    0.14
     Hum
    0.14
    Act Density 0.197%

    No Known Activations