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

    Neuronpedia

    INDEX
    Explanations

    words and phrases reflecting emotional experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.61
    ivably
    -0.58
    :^(
    -0.53
    脚注の使い方
    -0.53
    MigrationBuilder
    -0.52
     Réponses
    -0.51
     @"/
    -0.49
    maketitle
    -0.49
    équences
    -0.49
    EndContext
    -0.49
    POSITIVE LOGITS
     desire
    1.18
     love
    1.09
     thirst
    1.04
     passion
    0.96
     appetite
    0.95
    desire
    0.92
     appreciation
    0.92
     interest
    0.90
     craving
    0.90
     willingness
    0.89
    Act Density 0.384%

    No Known Activations