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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing gratitude or recognition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appreciated" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convol
    -0.72
    Race
    -0.67
     evict
    -0.65
     collide
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.63
    sche
    -0.62
     wrestle
    -0.61
     chase
    -0.61
     rewrite
    -0.61
     race
    -0.60
    POSITIVE LOGITS
     appreciated
    3.32
     emailed
    1.46
     admired
    1.37
     appreci
    1.04
    reci
    0.98
     loved
    0.98
     acknowledged
    0.89
     understood
    0.88
     liked
    0.87
     remembered
    0.87
    Act Density 0.014%

    No Known Activations