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

    Neuronpedia

    INDEX
    Explanations

    references to regulatory challenges and governance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اث
    -0.15
     intervention
    -0.15
    igrations
    -0.14
    社
    -0.13
     promises
    -0.13
    è¨Ģ
    -0.13
     stick
    -0.13
    tm
    -0.13
    borough
    -0.13
    icolon
    -0.13
    POSITIVE LOGITS
     capacity
    0.22
     Capacity
    0.21
     Harmon
    0.20
     harmon
    0.19
    capacity
    0.18
     capacities
    0.18
    _capacity
    0.18
    Capacity
    0.17
     Secret
    0.17
     Mutual
    0.17
    Act Density 0.056%

    No Known Activations