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

    Neuronpedia

    INDEX
    Explanations

    articulations of emotions or sentiments in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andre
    -0.17
    ocz
    -0.16
    ewire
    -0.16
    ycz
    -0.15
    oser
    -0.15
    orget
    -0.15
    ismet
    -0.15
    enville
    -0.14
    terra
    -0.14
    uchs
    -0.14
    POSITIVE LOGITS
    ĵ¨
    0.16
     Tender
    0.16
     reli
    0.15
     tender
    0.15
    assis
    0.14
    ip
    0.14
     Mons
    0.14
     massa
    0.13
     Emperor
    0.13
    .ip
    0.13
    Act Density 0.233%

    No Known Activations