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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "number" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARP
    -0.16
    ATUS
    -0.15
    cu
    -0.15
    elm
    -0.15
    ILLISECONDS
    -0.14
    asn
    -0.14
    arp
    -0.14
     bum
    -0.14
     Khu
    -0.13
    nx
    -0.13
    POSITIVE LOGITS
    allel
    0.15
    .Xaml
    0.15
    _tokenize
    0.15
    unction
    0.15
    vala
    0.15
     Vanity
    0.15
    ulton
    0.14
    adlo
    0.14
    aji
    0.14
     Pace
    0.14
    Act Density 0.024%

    No Known Activations