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

    Neuronpedia

    INDEX
    Explanations

    words related to demonstration or evidence of capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pData
    -0.17
    omo
    -0.17
    eler
    -0.16
    ابت
    -0.16
    omi
    -0.15
    ponsive
    -0.15
    amous
    -0.14
    iff
    -0.14
    itet
    -0.14
    inox
    -0.14
    POSITIVE LOGITS
    stration
    0.34
    strate
    0.28
    /demo
    0.19
    ikan
    0.17
    strar
    0.17
    iah
    0.16
    419
    0.16
     principle
    0.15
     Bread
    0.15
    ait
    0.15
    Act Density 0.024%

    No Known Activations