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

    Neuronpedia

    INDEX
    Explanations

    the term "further" and its variations, indicating an exploration or expansion of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     further
    -0.21
    sel
    -0.19
     Further
    -0.18
     weiter
    -0.18
    ses
    -0.18
    run
    -0.17
     furthermore
    -0.17
    shan
    -0.16
     farther
    -0.16
    sen
    -0.16
    POSITIVE LOGITS
    ance
    0.37
    ing
    0.35
     ado
    0.29
    most
    0.29
    -reaching
    0.28
    ed
    0.26
    nore
    0.23
    hin
    0.22
    -more
    0.22
    ANCE
    0.22
    Act Density 0.025%

    No Known Activations