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

    Neuronpedia

    INDEX
    Explanations

    entities and organizations related to social issues and sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntag
    -0.18
     Nat
    -0.18
     Nad
    -0.18
    Nx
    -0.17
    neh
    -0.17
    Nat
    -0.17
    nodoc
    -0.17
    ondo
    -0.17
    NX
    -0.17
    enne
    -0.17
    POSITIVE LOGITS
    ch
    0.23
    Ch
    0.19
     Wich
    0.18
     ch
    0.17
    chi
    0.16
    .ch
    0.16
    ycl
    0.16
    sh
    0.16
     Ch
    0.15
    ich
    0.15
    Act Density 0.066%

    No Known Activations