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

    Neuronpedia

    INDEX
    Explanations

    the word "at" in various contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     none
    -0.18
     every
    -0.17
     NONE
    -0.16
    uction
    -0.16
    eld
    -0.16
    lew
    -0.16
     EVERY
    -0.15
    laus
    -0.15
     each
    -0.15
     both
    -0.15
    POSITIVE LOGITS
     tall
    0.20
     ally
    0.18
     Raphael
    0.17
     Tall
    0.16
     ll
    0.16
     altogether
    0.15
    rawl
    0.15
    ally
    0.15
    skins
    0.15
    al
    0.14
    Act Density 0.012%

    No Known Activations