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

    Neuronpedia

    INDEX
    Explanations

    terms related to the meaning or definition of words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orie
    -0.72
    ength
    -0.70
    Catalog
    -0.69
    aire
    -0.69
    moil
    -0.68
     Sharing
    -0.68
    \-
    -0.67
    ener
    -0.67
    Merit
    -0.63
    agy
    -0.63
    POSITIVE LOGITS
     each
    1.07
     these
    0.96
     those
    0.87
     our
    0.85
     the
    0.85
     their
    0.81
     this
    0.77
     your
    0.74
     any
    0.72
     its
    0.71
    Act Density 0.253%

    No Known Activations