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

    Neuronpedia

    INDEX
    Explanations

    frequent occurrences of the word "a" followed by various attributes or descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.05
    ⓧ
    -1.03
    msgTypes
    -1.02
     виправивши
    -1.01
     Majefty
    -1.00
     myſelf
    -0.98
     tartalomajánló
    -0.98
    Демографія
    -0.94
     autorytatywna
    -0.94
     Monfieur
    -0.89
    POSITIVE LOGITS
     there
    0.93
     no
    0.68
     in
    0.68
     There
    0.68
     هناك
    0.67
    there
    0.61
    There
    0.60
     (
    0.58
     behind
    0.57
    on
    0.56
    Act Density 0.237%

    No Known Activations