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

    Neuronpedia

    INDEX
    Explanations

    references to demons and terms related to residence or analytics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iprot
    -0.71
    MessageOf
    -0.68
    SequentialGroup
    -0.67
    addCriterion
    -0.65
     виправивши
    -0.64
    :✨
    -0.64
    expandindo
    -0.64
    новништво
    -0.64
     témoig
    -0.64
    $_['
    -0.62
    POSITIVE LOGITS
     Demon
    0.52
     demon
    0.51
    Generated
    0.48
     constantemente
    0.37
     possam
    0.36
    Demon
    0.35
     semuanya
    0.35
     klingt
    0.35
    wapV
    0.34
    étend
    0.33
    Act Density 0.191%

    No Known Activations