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

    Neuronpedia

    INDEX
    Explanations

    references to past experiences and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     someday
    -0.15
    ignon
    -0.14
    _NEXT
    -0.14
     later
    -0.13
     Later
    -0.13
    later
    -0.13
    Later
    -0.12
    obel
    -0.12
    ãĤ¤ãĤ¯
    -0.12
    дÑĥ
    -0.12
    POSITIVE LOGITS
     prior
    0.72
     before
    0.64
    prior
    0.58
    Prior
    0.56
     previous
    0.55
     Prior
    0.55
    before
    0.54
     Before
    0.52
     BEFORE
    0.52
    Before
    0.51
    Act Density 0.393%

    No Known Activations