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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to horses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    |}{\
    -0.78
    cadilly
    -0.77
    _{-\
    -0.77
     Rides
    -0.76
     rides
    -0.72
    ride
    -0.72
     prit
    -0.71
    adaptiveStyles
    -0.71
     (!__
    -0.71
     تضيفلها
    -0.71
    POSITIVE LOGITS
    horses
    1.21
     horses
    1.16
    horse
    1.15
     horse
    1.08
     Horses
    1.06
    Horses
    1.04
    Horse
    0.96
     Horse
    0.93
     HORSE
    0.90
     equine
    0.78
    Act Density 0.004%

    No Known Activations