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

    Neuronpedia

    INDEX
    Explanations

    references to hotels

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Rend
    -0.71
     ADI
    -0.69
    Pars
    -0.68
    UnsafeEnabled
    -0.67
     Stow
    -0.67
    ||}
    -0.66
     Pars
    -0.65
     Cuenca
    -0.63
     CAV
    -0.63
    -0.63
    POSITIVE LOGITS
     Hotels
    1.42
     HOTEL
    1.38
     hotels
    1.36
    Hotels
    1.31
     Hotel
    1.29
    HOTEL
    1.27
     hotel
    1.23
     hoteles
    1.23
    hotel
    1.22
    Hotel
    1.15
    Act Density 0.003%

    No Known Activations