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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quality or satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elect
    -0.17
    yms
    -0.17
    elig
    -0.17
    yll
    -0.17
    ettes
    -0.17
    yen
    -0.16
    yonel
    -0.16
    Ø´ÙĨ
    -0.16
    igue
    -0.16
    ein
    -0.16
    POSITIVE LOGITS
    -known
    0.30
    spring
    0.28
    ington
    0.28
    ows
    0.26
    come
    0.22
    -being
    0.22
    -rounded
    0.20
    l
    0.20
    INGTON
    0.20
    inger
    0.19
    Act Density 0.072%

    No Known Activations