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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressing liking something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.57
    -0.49
    Anhalt
    -0.48
    ValueGeneration
    -0.47
     SwitchCompat
    -0.47
     }{@
    -0.46
    失礼
    -0.46
    Distribuzione
    -0.46
    AnchorTagHelper
    -0.46
    Personendaten
    -0.45
    POSITIVE LOGITS
     love
    0.75
     LOVE
    0.74
    Love
    0.72
    love
    0.70
    LOVE
    0.68
     Love
    0.64
     seeing
    0.63
     loved
    0.60
     watching
    0.59
     loves
    0.59
    Act Density 0.009%

    No Known Activations