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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to names and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     u
    -0.21
     en
    -0.21
     d
    -0.20
     ac
    -0.20
     b
    -0.20
     c
    -0.20
     l
    -0.20
     g
    -0.20
     r
    -0.20
     att
    -0.19
    POSITIVE LOGITS
    TRGL
    0.19
    okino
    0.18
     Parkway
    0.18
    ERRQ
    0.17
    iliki
    0.17
    arrera
    0.16
    tensorflow
    0.16
    ylko
    0.16
    BOOLE
    0.16
    oggler
    0.16
    Act Density 0.107%

    No Known Activations