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

    Neuronpedia

    INDEX
    Explanations

    phrases related to companionship and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.61
    esModule
    -0.43
    GeneratedCode
    -0.36
     Hosp
    -0.35
    fontawesome
    -0.34
     Boom
    -0.34
    yorsunuz
    -0.33
    DispatchToProps
    -0.33
    quiao
    -0.33
    afp
    -0.32
    POSITIVE LOGITS
    rungsseite
    0.66
    UnusedPrivate
    0.58
    帖最后由
    0.58
     ujednoznacz
    0.50
     otomatig
    0.49
    tagHelperRunner
    0.48
     للاسماء
    0.48
    Rüyada
    0.47
    uxxxx
    0.43
     EconPapers
    0.42
    Act Density 0.094%

    No Known Activations