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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and sentiments related to enjoyment or pleasure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyu
    -0.17
    bon
    -0.17
    agra
    -0.17
    bu
    -0.17
    plete
    -0.16
    501
    -0.16
    wi
    -0.16
    und
    -0.15
    trib
    -0.15
    ka
    -0.15
    POSITIVE LOGITS
    /lo
    0.19
     Lo
    0.19
    annis
    0.18
    elia
    0.18
    iola
    0.17
     ngại
    0.17
    aic
    0.17
    Lo
    0.17
    ely
    0.16
    eness
    0.16
    Act Density 0.011%

    No Known Activations