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

    Neuronpedia

    INDEX
    Explanations

    the concept of mechanisms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tramonto
    -0.81
     suspensão
    -0.77
    ingly
    -0.75
     McMillan
    -0.74
     Universitaria
    -0.73
     monasterio
    -0.73
     Ambro
    -0.73
     Travers
    -0.72
     abandonné
    -0.72
     Füßen
    -0.72
    POSITIVE LOGITS
     NOISE
    0.92
     Noise
    0.76
     noisy
    0.76
    riwal
    0.73
     noise
    0.73
     Mechanisms
    0.72
     Eisenberg
    0.71
    Eisen
    0.71
     ря
    0.71
    mechanism
    0.70
    Act Density 0.077%

    No Known Activations