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

    Neuronpedia

    INDEX
    Explanations

    occurrences of formal language pertaining to rules, regulations, and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Writer
    -0.16
    hit
    -0.15
    éij
    -0.14
     Visitor
    -0.14
    listed
    -0.14
    ạp
    -0.14
     Speedway
    -0.13
    Ø·ÙĨ
    -0.13
    borg
    -0.13
     listings
    -0.13
    POSITIVE LOGITS
    forward
    0.24
     sent
    0.24
     forward
    0.23
     forwarded
    0.22
     shared
    0.22
     Forward
    0.21
    Forward
    0.21
     presented
    0.21
     handed
    0.21
     distributed
    0.21
    Act Density 0.137%

    No Known Activations