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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "at" with varying frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gether
    -0.21
    lessly
    -0.21
    iance
    -0.19
    theless
    -0.16
    ducted
    -0.16
    etheless
    -0.16
    jure
    -0.16
    culate
    -0.15
    mary
    -0.15
    nehmen
    -0.15
    POSITIVE LOGITS
     most
    0.18
     LE
    0.18
    otal
    0.18
     lease
    0.17
    endency
    0.17
    eam
    0.16
     east
    0.16
    mega
    0.16
    elect
    0.16
    &t
    0.15
    Act Density 0.034%

    No Known Activations