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

    Neuronpedia

    INDEX
    Explanations

    phrases related to boats and water activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     krab
    -0.90
     klap
    -0.84
     ananas
    -0.75
     kombi
    -0.74
     drap
    -0.74
     hek
    -0.73
     dora
    -0.73
     vola
    -0.73
     apparente
    -0.72
     impon
    -0.71
    POSITIVE LOGITS
     boat
    1.27
    boat
    1.26
     boats
    1.12
    Boat
    1.10
    boats
    1.08
     Boat
    1.06
     Boats
    0.92
    Boats
    0.90
     BOAT
    0.89
     boating
    0.82
    Act Density 0.093%

    No Known Activations