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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional complexity and relationship dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyu
    -0.17
    ç©
    -0.15
    ulta
    -0.15
    ugal
    -0.15
    ersistence
    -0.14
     HÃłnh
    -0.14
    '])){
    -0.14
    ogui
    -0.14
    weet
    -0.14
    .Parcelable
    -0.14
    POSITIVE LOGITS
     love
    0.25
     loves
    0.20
     respect
    0.20
    æĦĽ
    0.20
     affection
    0.19
     adore
    0.19
    Love
    0.19
     lo
    0.19
     Love
    0.18
    -lo
    0.18
    Act Density 0.210%

    No Known Activations