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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment and enthusiasm related to experiences or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .swagger
    -0.15
    inee
    -0.15
    ãģijãģªãģĦ
    -0.15
     therefore
    -0.14
    askell
    -0.14
    iska
    -0.14
     reign
    -0.14
    uge
    -0.14
    ilarity
    -0.14
     Nope
    -0.13
    POSITIVE LOGITS
     especially
    0.21
    especially
    0.19
     considering
    0.16
     pity
    0.16
    nic
    0.15
     esp
    0.15
     Especially
    0.15
    (equal
    0.15
    esp
    0.15
    ãĥªãĥ¼ãĤº
    0.15
    Act Density 0.322%

    No Known Activations