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

    Neuronpedia

    INDEX
    Explanations

    references to membership and activity statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.82
    azeera
    -0.79
    .}
    -0.78
    lems
    -0.72
    lins
    -0.70
    paren
    -0.67
     WATCHED
    -0.66
     Collider
    -0.65
    fters
    -0.64
    aughs
    -0.64
    POSITIVE LOGITS
     VPN
    1.00
     SSL
    0.83
    SSL
    0.82
    VPN
    0.82
     downgrade
    0.81
     Asus
    0.77
     WiFi
    0.75
     UDP
    0.74
     Acer
    0.74
     AES
    0.72
    Act Density 0.074%

    No Known Activations