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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific concepts and measurements in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rocket
    -0.17
    Rocket
    -0.16
    551
    -0.15
    лÑĥÑĩ
    -0.15
     ãĤ¢ãĤ¤
    -0.15
    éĬ
    -0.14
     rocket
    -0.14
    rocket
    -0.14
     Electron
    -0.14
    гоÑĢ
    -0.14
    POSITIVE LOGITS
     rhe
    0.29
     collo
    0.26
     vis
    0.25
     Rhe
    0.25
     jam
    0.24
     susp
    0.22
    gel
    0.22
     glass
    0.21
     col
    0.21
    jam
    0.21
    Act Density 0.007%

    No Known Activations