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

    Neuronpedia

    INDEX
    Explanations

    phrases related to additional information or extra details

    oai_token-act-pair · gpt-3.5-turbo

    the word "also" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hundred
    -0.68
     tens
    -0.66
     mere
    -0.65
     quarter
    -0.64
     thousands
    -0.62
     hundreds
    -0.61
     decades
    -0.61
     weeks
    -0.61
     hours
    -0.61
     barriers
    -0.60
    POSITIVE LOGITS
     Also
    3.28
    Also
    2.39
     ALSO
    2.29
     Additionally
    2.07
     Secondly
    1.90
     Lastly
    1.85
     Furthermore
    1.81
     Moreover
    1.71
    also
    1.68
     Besides
    1.64
    Act Density 0.020%

    No Known Activations