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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific names, pronouns, and punctuation that suggest personal or emotional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wilmington
    -0.17
     Dou
    -0.16
    á»ĵng
    -0.15
    517
    -0.15
    esc
    -0.15
    antu
    -0.15
    iska
    -0.14
    b
    -0.14
    erp
    -0.14
     Median
    -0.14
    POSITIVE LOGITS
    è³¢
    0.15
    _Msg
    0.15
    urdy
    0.14
    álo
    0.14
    idas
    0.14
    osite
    0.14
    Truthy
    0.14
     Poh
    0.13
    _assets
    0.13
    <typeof
    0.13
    Act Density 0.001%

    No Known Activations