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

    Neuronpedia

    INDEX
    Explanations

    terms related to user interaction, sign-up processes, and notifications

    oai_token-act-pair · gpt-3.5-turbo

    user account-related actions and statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APS
    -0.63
    åħī
    -0.62
    ioned
    -0.60
    Eva
    -0.56
     frank
    -0.56
    Frank
    -0.56
    inis
    -0.56
    ecd
    -0.55
    entimes
    -0.55
    ongevity
    -0.55
    POSITIVE LOGITS
     hereby
    0.87
     browser
    0.86
     javascript
    0.79
     Login
    0.79
     Browser
    0.78
     Javascript
    0.74
     Password
    0.72
     guessed
    0.72
     JavaScript
    0.69
     requested
    0.69
    Act Density 0.165%

    No Known Activations