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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to medical conditions and technical jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    m
    -0.87
    ness
    -0.75
    s
    -0.71
    ly
    -0.70
    ms
    -0.69
    baix
    -0.68
    r
    -0.68
    ting
    -0.66
    ling
    -0.65
    us
    -0.65
    POSITIVE LOGITS
    auso
    1.04
     purpoſe
    0.99
     Dooley
    0.99
     Quo
    0.97
    eo
    0.96
     Malo
    0.96
     Rollo
    0.94
     Mojo
    0.94
     Ando
    0.93
     Puro
    0.93
    Act Density 0.844%

    No Known Activations