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

    Neuronpedia

    INDEX
    Explanations

    the word "Spa" or related variations indicating a spa or relaxation context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letes
    -0.17
    uted
    -0.17
     Bren
    -0.16
     spare
    -0.16
     Hod
    -0.15
    ps
    -0.15
    erase
    -0.15
    anke
    -0.15
    qu
    -0.15
    patial
    -0.14
    POSITIVE LOGITS
    itzer
    0.22
    RING
    0.20
    emann
    0.20
    elman
    0.20
    otted
    0.20
    illo
    0.19
    rou
    0.19
    cies
    0.17
     Sp
    0.17
    arta
    0.17
    Act Density 0.023%

    No Known Activations