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

    Neuronpedia

    INDEX
    Explanations

    the presence of commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.69
    #$
    -0.68
     tyr
    -0.63
    elligent
    -0.63
    efe
    -0.63
    arat
    -0.62
    -+-+
    -0.61
     "$:/
    -0.61
    obin
    -0.61
    ishly
    -0.60
    POSITIVE LOGITS
     please
    0.72
     purposes
    0.67
    include
    0.64
     visit
    0.63
     Cox
    0.62
     Nil
    0.60
     supplemented
    0.59
     consider
    0.58
     recourse
    0.58
     sake
    0.57
    Act Density 0.094%

    No Known Activations