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

    Neuronpedia

    INDEX
    Explanations

    references to experiments or experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.81
     desmotivaciones
    -0.80
     solteiro
    -0.75
    attutto
    -0.75
     dezelve
    -0.74
     idéia
    -0.74
    berdayakan
    -0.74
    ſammen
    -0.73
    ulgação
    -0.73
    ambién
    -0.73
    POSITIVE LOGITS
     experiment
    0.79
     experimental
    0.75
     experimentally
    0.74
    experiment
    0.60
     Experimental
    0.59
     Experiment
    0.59
    Experimental
    0.57
    experimental
    0.55
    Experiment
    0.53
     start
    0.52
    Act Density 0.259%

    No Known Activations