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

    Neuronpedia

    INDEX
    Explanations

    instances of static or fixed values in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.63
     Italijanski
    -0.55
    Jîn
    -0.52
     Perfectly
    -0.51
    ItemBackground
    -0.50
    RegistryLite
    -0.49
     perfectly
    -0.49
    Perfectly
    -0.47
    fjspx
    -0.46
     Mountain
    -0.45
    POSITIVE LOGITS
     broadcast
    0.49
     broadcasting
    0.47
     Broadcast
    0.45
     BUILDINGS
    0.44
     buildings
    0.44
    Broadcast
    0.44
     Broadcasting
    0.43
     Tweets
    0.42
     tweets
    0.42
    0.42
    Act Density 0.022%

    No Known Activations