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

    Neuronpedia

    INDEX
    Explanations

    expressions of joy and pleasure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AKE
    -0.15
     Cra
    -0.15
    ell
    -0.15
    ngx
    -0.14
     Orr
    -0.14
    aoke
    -0.14
    rov
    -0.14
    HELL
    -0.14
     Ray
    -0.13
    arine
    -0.13
    POSITIVE LOGITS
    fully
    0.26
    ably
    0.18
    FUL
    0.17
    ¼
    0.17
    ful
    0.17
    FULL
    0.17
    fulness
    0.16
    oader
    0.16
    Ïīδ
    0.15
    ous
    0.15
    Act Density 0.068%

    No Known Activations