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

    Neuronpedia

    INDEX
    Explanations

    checkboxes to verify if a user is human

    oai_token-act-pair · gpt-3.5-turbo

    actions related to user verification and interaction with web forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perspect
    -0.74
    aimon
    -0.73
    ivas
    -0.72
    ufact
    -0.67
    gart
    -0.65
    phen
    -0.64
     helic
    -0.64
     oun
    -0.64
    rolog
    -0.64
    vironments
    -0.62
    POSITIVE LOGITS
     Subscribe
    0.73
     isEnabled
    0.73
    Subscribe
    0.72
     [+]
    0.69
    interstitial
    0.68
     guiActive
    0.67
     Errors
    0.67
     Ø
    0.66
    iframe
    0.65
     è£ıè
    0.65
    Act Density 0.024%

    No Known Activations