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

    Neuronpedia

    INDEX
    Explanations

    words associated with conflict and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edList
    -0.14
     spite
    -0.14
    QA
    -0.13
    stype
    -0.13
    ÑģÑĤи
    -0.13
    .toolStripSeparator
    -0.13
     dostate
    -0.13
    OrCreate
    -0.12
    anden
    -0.12
    rende
    -0.12
    POSITIVE LOGITS
    ivor
    0.16
    usch
    0.15
    Inspectable
    0.14
    ehler
    0.14
    ouch
    0.14
    ihar
    0.14
     Verd
    0.14
     PSU
    0.13
     Pruitt
    0.13
    PPER
    0.13
    Act Density 0.014%

    No Known Activations