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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distinguishing, comparing, or identifying differences between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yz
    -0.16
    155
    -0.15
    æĤŁ
    -0.15
    ideo
    -0.15
    ico
    -0.14
    acity
    -0.14
    tings
    -0.14
    ĭ
    -0.14
    ando
    -0.14
    ome
    -0.14
    POSITIVE LOGITS
    ively
    0.29
     between
    0.23
     apart
    0.22
    difference
    0.20
    iveness
    0.20
    mere
    0.20
     distinction
    0.20
     difference
    0.19
     Between
    0.19
    between
    0.19
    Act Density 0.057%

    No Known Activations