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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "of" indicating relationships or connections

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

    superlative/number of group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.54
    Попис
    -0.48
    帖最后由
    -0.46
     quæ
    -0.46
     للمعارف
    -0.43
     enfans
    -0.43
    intios
    -0.42
     tartalomajánló
    -0.42
     mxArray
    -0.42
    MigrationBuilder
    -0.41
    POSITIVE LOGITS
     among
    0.72
     amongst
    0.72
    among
    0.66
     AMONG
    0.58
     Amongst
    0.58
     parmi
    0.54
     blandt
    0.53
     Among
    0.51
    Among
    0.49
     blant
    0.47
    Act Density 0.243%

    No Known Activations