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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and references in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Merz
    -0.83
     Pyle
    -0.79
    ombic
    -0.77
    AsUp
    -0.76
     Elliott
    -0.76
     Pernambuco
    -0.76
     endom
    -0.74
    Elliott
    -0.74
     Gonçalves
    -0.74
    wahati
    -0.73
    POSITIVE LOGITS
    mány
    0.83
     Teb
    0.79
     Coates
    0.77
     Petrov
    0.76
     tomatoes
    0.75
     Barrera
    0.75
     Bohn
    0.74
     Ve
    0.74
    ècie
    0.72
     Frid
    0.72
    Act Density 8.335%

    No Known Activations