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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal education and training processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    radu
    -0.16
    ozilla
    -0.15
    riad
    -0.15
    xca
    -0.14
    arkan
    -0.14
    бÑĢа
    -0.14
    atatype
    -0.14
    Advertis
    -0.14
    å®Ĺ
    -0.13
     gravity
    -0.13
    POSITIVE LOGITS
    ee
    0.73
    ees
    0.68
    eee
    0.47
     ee
    0.46
    ée
    0.45
    tees
    0.44
    tee
    0.44
    EE
    0.42
    ées
    0.39
    nee
    0.38
    Act Density 0.029%

    No Known Activations