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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols that may denote a particular digital or textual format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Microwave
    -0.14
     гÑĢаж
    -0.13
    okia
    -0.13
     Workers
    -0.13
     Semiconductor
    -0.13
    침
    -0.13
     Nuclear
    -0.13
    ombie
    -0.13
    à¤Ĺर
    -0.12
    .mongodb
    -0.12
    POSITIVE LOGITS
     horses
    0.52
     horse
    0.52
     Horse
    0.47
    horse
    0.43
     rider
    0.43
     riders
    0.42
     riding
    0.38
     Riders
    0.37
     saddle
    0.35
     Riding
    0.35
    Act Density 0.003%

    No Known Activations