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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases expressing value, worth, or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dap
    -0.47
    спери
    -0.47
     Opal
    -0.46
    XCT
    -0.46
     MonoBehaviour
    -0.45
     malin
    -0.45
    jestic
    -0.45
     Pompey
    -0.44
     reporta
    -0.43
     torchvision
    -0.43
    POSITIVE LOGITS
     any
    1.26
     anything
    1.14
     qualsiasi
    1.08
     qualquer
    1.04
     cualquier
    1.04
     qualunque
    0.98
    任何
    0.96
     anyone
    0.93
    anything
    0.93
     quaisquer
    0.93
    Act Density 0.163%

    No Known Activations