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

    Neuronpedia

    INDEX
    Explanations

    references to soap

    oai_token-act-pair · gpt-3.5-turbo

    references to soap and its production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issued
    -0.68
    etermined
    -0.67
    sen
    -0.65
    interrupted
    -0.64
    trl
    -0.62
     sworn
    -0.61
    ooming
    -0.61
    classified
    -0.61
    rals
    -0.60
    uding
    -0.60
    POSITIVE LOGITS
     soap
    1.30
     opera
    1.08
     oper
    0.98
    ãĤ¦ãĤ¹
    0.94
    glers
    0.84
     yarn
    0.80
    utical
    0.79
     Pengu
    0.77
     Bunny
    0.75
    combe
    0.74
    Act Density 0.009%

    No Known Activations