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

    Neuronpedia

    INDEX
    Explanations

    terms related to emotional expressions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mayer
    -0.14
    aster
    -0.14
     Gros
    -0.14
    isel
    -0.14
     styl
    -0.14
    .LookAndFeel
    -0.14
    ential
    -0.13
     Aires
    -0.13
    unn
    -0.13
     Lexer
    -0.13
    POSITIVE LOGITS
    rung
    0.15
    elyn
    0.15
    eren
    0.14
    contre
    0.14
    enet
    0.14
    'gc
    0.14
     bou
    0.14
    owell
    0.14
    culus
    0.13
    eczy
    0.13
    Act Density 0.028%

    No Known Activations