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

    Neuronpedia

    INDEX
    Explanations

    expressions conveying feelings of disappointment or negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DDD
    -0.16
    opath
    -0.16
    active
    -0.15
    stab
    -0.14
    ालय
    -0.14
    ique
    -0.14
    Ñĩа
    -0.14
    ovsky
    -0.14
    atham
    -0.14
    itis
    -0.14
    POSITIVE LOGITS
    fully
    0.22
    FUL
    0.20
    fulness
    0.19
    akening
    0.19
     aw
    0.18
    akens
    0.17
    arde
    0.17
     Aw
    0.17
    ful
    0.17
    .githubusercontent
    0.17
    Act Density 0.014%

    No Known Activations