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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases conveying warmth and positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auge
    -0.17
    idal
    -0.16
    innacle
    -0.16
    ifen
    -0.15
    ritis
    -0.15
    erence
    -0.14
    sse
    -0.14
    culus
    -0.14
    olls
    -0.14
    aurus
    -0.14
    POSITIVE LOGITS
    est
    0.37
    -blood
    0.33
    heart
    0.31
    ong
    0.30
     fuzzy
    0.29
    blood
    0.29
    -hearted
    0.28
    th
    0.28
     fuzz
    0.27
    ers
    0.27
    Act Density 0.024%

    No Known Activations