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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "other" and its variations, indicating comparisons or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icle
    -0.16
     lain
    -0.15
    cken
    -0.15
    adaÅŁ
    -0.14
    swers
    -0.14
    ý
    -0.13
    rong
    -0.13
    ittest
    -0.13
     both
    -0.13
    rick
    -0.13
    POSITIVE LOGITS
    -than
    0.40
    world
    0.35
     than
    0.34
     similar
    0.32
     similarly
    0.32
    wis
    0.30
    ewise
    0.30
     equally
    0.28
    -world
    0.27
    than
    0.26
    Act Density 0.113%

    No Known Activations