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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing gratitude or approval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compuls
    -0.94
    infect
    -0.91
    voy
    -0.80
    metal
    -0.79
    shr
    -0.79
    dest
    -0.77
    sil
    -0.75
    orig
    -0.73
    prep
    -0.71
    smoking
    -0.71
    POSITIVE LOGITS
     appreciation
    1.21
     appreciate
    1.20
     appreciated
    1.04
    ĸļ
    0.95
     appreci
    0.94
     compliments
    0.80
     appre
    0.79
    awaru
    0.78
    ð
    0.77
    ¿½
    0.77
    Act Density 0.009%

    No Known Activations