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

    "appreciate" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    appreciate you, your, it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    -0.61
    yn
    -0.57
    ing
    -0.53
    q
    -0.53
     Mog
    -0.53
     lign
    -0.51
    TagHelper
    -0.51
    tellungs
    -0.50
    T
    -0.50
     death
    -0.50
    POSITIVE LOGITS
    reciate
    0.85
     appreciate
    0.83
    reciation
    0.83
     Appreciate
    0.82
     appreciates
    0.78
     appreciative
    0.75
     appreciated
    0.75
     GetEnumerator
    0.74
     appreci
    0.74
    appreciated
    0.73
    Act Density 0.060%

    No Known Activations