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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "including."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ai
    -0.78
    acket
    -0.76
    aya
    -0.75
    esa
    -0.72
    cel
    -0.70
    gor
    -0.70
    peg
    -0.69
    erv
    -0.69
    assian
    -0.68
    agne
    -0.68
    POSITIVE LOGITS
     ones
    0.91
     yours
    0.91
     ours
    0.88
     those
    0.87
     hers
    0.84
     mine
    0.75
     possibly
    0.75
     vice
    0.72
     theirs
    0.69
     incidentally
    0.64
    Act Density 0.118%

    No Known Activations