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

    Neuronpedia

    INDEX
    Explanations

    references to hotels and accommodations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eden
    -0.16
    еÑĢеж
    -0.16
    itten
    -0.15
     kelim
    -0.15
     côt
    -0.15
    Compound
    -0.15
    itage
    -0.15
    irut
    -0.15
    artment
    -0.14
     compound
    -0.14
    POSITIVE LOGITS
     Econ
    0.19
     mot
    0.18
     interstate
    0.17
     IH
    0.17
    coni
    0.16
     universities
    0.16
     Choice
    0.16
     pet
    0.16
     Battlefield
    0.16
     Petro
    0.15
    Act Density 0.081%

    No Known Activations