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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pály
    -0.49
     solchen
    -0.47
     cualquiera
    -0.44
     niż
    -0.42
     cuna
    -0.42
     molta
    -0.42
     facie
    -0.42
     deur
    -0.42
     rather
    -0.41
     instala
    -0.39
    POSITIVE LOGITS
     remaining
    1.09
    remaining
    0.96
     aforementioned
    0.85
    ReusableCell
    0.79
    maining
    0.79
    uminense
    0.77
     newest
    0.76
     Remaining
    0.76
    iniest
    0.76
    UnusedPrivate
    0.75
    Act Density 0.229%

    No Known Activations