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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific components and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.51
    oa̍t
    -0.48
     Vikipedi
    -0.45
     więc
    -0.45
     Meaning
    -0.44
    Meaning
    -0.44
    Hentet
    -0.43
     precludes
    -0.43
     bởi
    -0.42
    ktm
    -0.41
    POSITIVE LOGITS
     releasing
    1.07
     gaining
    1.02
     depositing
    1.01
     bringing
    0.99
     seizing
    0.98
     turning
    0.98
     destroying
    0.97
     acquiring
    0.96
     sending
    0.95
     obtaining
    0.95
    Act Density 0.954%

    No Known Activations