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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quality or effectiveness in performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yms
    -0.18
    emic
    -0.17
    Ø´ÙĨ
    -0.17
    elig
    -0.17
    elect
    -0.17
    yll
    -0.17
    eum
    -0.16
    elige
    -0.16
    eous
    -0.16
    yled
    -0.15
    POSITIVE LOGITS
    -known
    0.31
    spring
    0.29
    ington
    0.28
    ows
    0.25
    -being
    0.25
    -rounded
    0.21
    come
    0.21
    known
    0.20
    -defined
    0.19
    being
    0.19
    Act Density 0.072%

    No Known Activations