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

    Neuronpedia

    INDEX
    Explanations

    references to bars or similar establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kul
    -0.21
    kiego
    -0.17
    empo
    -0.17
    ene
    -0.17
    kup
    -0.16
    kr
    -0.15
    kola
    -0.15
    enant
    -0.15
    eners
    -0.15
    gang
    -0.15
    POSITIVE LOGITS
    bara
    0.28
    oque
    0.25
    tering
    0.24
    coded
    0.24
     Harbor
    0.24
    riers
    0.23
    coding
    0.23
    tered
    0.22
    becue
    0.22
    rios
    0.22
    Act Density 0.012%

    No Known Activations