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

    Neuronpedia

    INDEX
    Explanations

    the presence of the prefix "che" which is indicative of chemical or chemical-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    chelator, chemoreceptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
    ítmény
    -0.46
     resource
    -0.43
    álen
    -0.43
     Wolfs
    -0.43
     Naturs
    -0.42
    goTo
    -0.41
    kait
    -0.41
    nement
    -0.41
    isbury
    -0.40
    POSITIVE LOGITS
     che
    1.55
     Che
    1.10
    Che
    1.04
     CHE
    0.96
    CHE
    0.91
    che
    0.89
     Chet
    0.76
     cheques
    0.74
     chemo
    0.74
     ché
    0.74
    Act Density 0.002%

    No Known Activations