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

    Neuronpedia

    INDEX
    Explanations

    positive feedback about a hotel or lodging experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leo
    -0.18
    icates
    -0.14
     rejected
    -0.14
     brick
    -0.14
    iedo
    -0.14
    etail
    -0.13
    elic
    -0.13
    umont
    -0.13
    ä¸ĩ
    -0.13
     Gregory
    -0.13
    POSITIVE LOGITS
    ниÑĤ
    0.14
     Spo
    0.14
    iles
    0.14
    ILES
    0.14
    .mk
    0.14
    lerdi
    0.14
     Parkway
    0.14
    اجات
    0.14
    ozor
    0.14
    aira
    0.13
    Act Density 0.168%

    No Known Activations