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

    Neuronpedia

    INDEX
    Explanations

    references to hydrogen and its various forms and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UDO
    -0.16
    fé
    -0.15
    aign
    -0.14
    RunWith
    -0.14
     cogn
    -0.14
    à¥įà¤Łà¤®
    -0.14
    mux
    -0.14
     AUX
    -0.14
    umont
    -0.14
     carbon
    -0.14
    POSITIVE LOGITS
    ated
    0.37
    ation
    0.29
     gas
    0.27
    ase
    0.26
    ATED
    0.25
     atoms
    0.24
    ating
    0.24
     atom
    0.23
    ous
    0.21
    ases
    0.20
    Act Density 0.020%

    No Known Activations