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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "continue" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pearance
    -0.14
    steen
    -0.14
    arna
    -0.14
    amba
    -0.14
    rap
    -0.14
    ãİ¡
    -0.13
    arme
    -0.13
    ;amp
    -0.13
    tery
    -0.13
    rupt
    -0.13
    POSITIVE LOGITS
    egative
    0.18
    arily
    0.16
    aneously
    0.15
    apolis
    0.15
    ÙĦس
    0.15
    aneous
    0.15
    indre
    0.15
    ä¸ĭåİ»
    0.14
    valid
    0.14
    ="{!!
    0.14
    Act Density 0.062%

    No Known Activations