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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or official contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.27
    ted
    -0.26
    eds
    -0.25
    ED
    -0.24
    ед
    -0.22
    eding
    -0.20
    edb
    -0.20
    edin
    -0.20
    eded
    -0.18
    ded
    -0.18
    POSITIVE LOGITS
    en
    0.27
    ene
    0.21
    enes
    0.20
    enen
    0.19
    ngen
    0.18
    ener
    0.18
    angen
    0.18
    een
    0.17
    len
    0.17
    ken
    0.16
    Act Density 0.029%

    No Known Activations