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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to responsibility and action in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bookmark
    -0.16
    jak
    -0.16
    esel
    -0.14
    iid
    -0.14
    berg
    -0.14
    egal
    -0.14
    hower
    -0.14
    eg
    -0.14
    aded
    -0.14
    icha
    -0.14
    POSITIVE LOGITS
    UME
    0.15
    rie
    0.14
    BILE
    0.14
     åĽ
    0.14
     DeV
    0.13
    ume
    0.13
     Nem
    0.13
    VEC
    0.13
    izes
    0.13
    ige
    0.13
    Act Density 0.166%

    No Known Activations