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

    Neuronpedia

    INDEX
    Explanations

    sentences describing back-and-forth movement

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "back and forth" or similar repetitive structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ible
    -0.68
    oret
    -0.67
    ãĤª
    -0.66
     sqor
    -0.66
    merce
    -0.65
     Tradable
    -0.65
    士
    -0.65
     NETWORK
    -0.64
    ZA
    -0.63
    emouth
    -0.62
    POSITIVE LOGITS
     forth
    1.93
    forth
    1.18
     Forth
    1.17
     forwards
    0.86
     thirds
    0.75
     aft
    0.74
     forward
    0.74
     again
    0.74
    Charges
    0.73
     sideways
    0.67
    Act Density 0.041%

    No Known Activations