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

    Neuronpedia

    INDEX
    Explanations

    words and concepts related to pain and suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thor
    -0.17
     svens
    -0.16
     ragaz
    -0.15
    طر
    -0.14
    swick
    -0.14
     bü
    -0.14
    eki
    -0.14
     Kinder
    -0.14
    iyas
    -0.14
    VERS
    -0.14
    POSITIVE LOGITS
    avis
    0.19
    igh
    0.18
     avis
    0.18
    aler
    0.17
    ighet
    0.17
    IGH
    0.16
    AGIC
    0.15
     og
    0.15
    ailer
    0.15
    emet
    0.15
    Act Density 0.353%

    No Known Activations