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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a continuous action or progression over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    polator
    -0.16
    igaret
    -0.16
    ymb
    -0.16
    optera
    -0.15
    xin
    -0.14
    بÙĬÙĨ
    -0.14
    ierce
    -0.14
    ãĥªãĤ¹
    -0.14
    LineNumber
    -0.14
    icerca
    -0.14
    POSITIVE LOGITS
     onto
    0.24
     proceeded
    0.20
     Ont
    0.19
     gone
    0.18
     proceeds
    0.18
    went
    0.17
     went
    0.17
     proceed
    0.17
     ont
    0.17
     Proceed
    0.16
    Act Density 0.012%

    No Known Activations