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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or comparison over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to recurrence and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.75
    pmwiki
    -0.65
    lez
    -0.64
     Stall
    -0.62
    mare
    -0.62
    mic
    -0.61
    obar
    -0.61
    oft
    -0.60
    ilan
    -0.58
     Cycling
    -0.58
    POSITIVE LOGITS
    ãĢĤ
    0.74
    .</
    0.66
    .}
    0.65
    .''.
    0.64
    .''
    0.63
    ,''
    0.62
     relies
    0.62
     attracted
    0.62
     è£ı
    0.62
     resulting
    0.62
    Act Density 0.208%

    No Known Activations