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

    Neuronpedia

    INDEX
    Explanations

    references to people and their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Humanity
    -0.74
     SAN
    -0.72
     LINE
    -0.70
     SERV
    -0.70
     Guid
    -0.69
     Directions
    -0.69
     FAC
    -0.67
     Curt
    -0.67
     CLA
    -0.67
     Patron
    -0.67
    POSITIVE LOGITS
    addon
    1.09
    dq
    1.04
    _
    0.94
    wo
    0.94
    admin
    0.93
    ethe
    0.93
    py
    0.92
    online
    0.91
    erie
    0.91
    internet
    0.89
    Act Density 0.035%

    No Known Activations