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-3.5-turbo
    New Auto-Interp
    Negative Logits
    toggle
    -0.84
    NULL
    -0.76
    aq
    -0.76
    Enlarge
    -0.67
    antz
    -0.66
    addafi
    -0.66
    Diff
    -0.66
    irting
    -0.63
    cigarettes
    -0.63
    lash
    -0.63
    POSITIVE LOGITS
     hopefully
    1.03
     secondly
    0.97
     congr
    0.85
     deserve
    0.83
     welcomes
    0.82
     strive
    0.79
     luckily
    0.79
    ï¸ı
    0.79
     ours
    0.78
     congratulate
    0.78
    Act Density 0.296%

    No Known Activations