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

    Neuronpedia

    INDEX
    Explanations

    references to user interactions with online content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ers
    -0.16
    haus
    -0.16
    ut
    -0.15
    ored
    -0.15
    uch
    -0.15
    auge
    -0.15
    unned
    -0.14
    arkin
    -0.14
    enders
    -0.14
    quirer
    -0.14
    POSITIVE LOGITS
     Responses
    0.19
     responses
    0.18
     Spy
    0.17
    Responses
    0.16
     track
    0.16
    à¹Ħล
    0.16
     Track
    0.15
    esson
    0.15
     feed
    0.15
    Track
    0.15
    Act Density 0.005%

    No Known Activations