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

    Neuronpedia

    INDEX
    Explanations

    email verification prompts

    oai_token-act-pair · gpt-3.5-turbo

    prompts related to email entry and validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    accompan
    -0.61
    ccording
    -0.61
    è¦ļéĨĴ
    -0.59
     chopping
    -0.55
     promul
    -0.53
    eatures
    -0.53
     declass
    -0.52
    senal
    -0.50
     tremend
    -0.50
    idious
    -0.50
    POSITIVE LOGITS
    prise
    0.78
    tainment
    0.65
    ãĤº
    0.60
    xon
    0.58
     isEnabled
    0.58
    forge
    0.58
     Latvia
    0.58
    iframe
    0.58
    myra
    0.57
    prises
    0.56
    Act Density 0.007%

    No Known Activations