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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĥr
    -0.16
    uben
    -0.14
    enny
    -0.14
    ש
    -0.14
    aint
    -0.14
     Rubin
    -0.13
    ecast
    -0.13
    lator
    -0.13
    quee
    -0.13
    castle
    -0.13
    POSITIVE LOGITS
    ÏģÏĮ
    0.14
     Îŀ
    0.13
    ijken
    0.13
     Sher
    0.13
    />.↵↵
    0.13
    iesz
    0.13
    alk
    0.13
     Velvet
    0.12
    θή
    0.12
    ès
    0.12
    Act Density 0.284%

    No Known Activations