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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and references to studies or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſever
    -0.67
     ſta
    -0.66
     Diſ
    -0.63
     unſ
    -0.63
     Anſ
    -0.62
     Reſ
    -0.62
     Houſe
    -0.62
     ſy
    -0.62
     houſe
    -0.61
     tranſ
    -0.60
    POSITIVE LOGITS
     sementes
    0.60
     giapp
    0.59
     titolata
    0.52
     árvores
    0.51
     varones
    0.50
     tæ
    0.50
     termica
    0.50
     nocturno
    0.50
     spalle
    0.49
     retrô
    0.49
    Act Density 0.525%

    No Known Activations