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

    Neuronpedia

    INDEX
    Explanations

    concepts related to health, safety, and community well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¥
    -0.17
    _unused
    -0.16
    çĹĩ
    -0.15
    anza
    -0.15
    ÙĪÙĦا
    -0.14
     symptom
    -0.14
    ikel
    -0.14
    esters
    -0.14
    tober
    -0.14
    ardon
    -0.14
    POSITIVE LOGITS
     questioned
    0.22
     evapor
    0.21
     jeopardy
    0.20
     endangered
    0.20
     jeopard
    0.18
     compromised
    0.18
    -question
    0.17
    iol
    0.17
     challenged
    0.17
     sacrificed
    0.17
    Act Density 0.218%

    No Known Activations