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

    Neuronpedia

    INDEX
    Explanations

    terms related to maximum values or limits across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sci
    -0.50
     Sci
    -0.50
    appartamento
    -0.44
     Jel
    -0.42
    sci
    -0.42
     folks
    -0.42
    wendi
    -0.41
     enfri
    -0.41
    fluffy
    -0.40
     sci
    -0.40
    POSITIVE LOGITS
     maximum
    1.55
    maximum
    1.51
    Maximum
    1.46
     Maximum
    1.45
     MAXIMUM
    1.27
    MAXIMUM
    1.20
     maxim
    1.14
     minimum
    1.13
    Minimum
    1.10
     maximal
    1.09
    Act Density 0.216%

    No Known Activations