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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or processes that are in progress or being carried out

    oai_token-act-pair · gpt-3.5-turbo

    actions and statuses related to ongoing efforts or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aint
    -0.71
    Imagine
    -0.66
     qualifies
    -0.64
    âĶ
    -0.63
     resear
    -0.62
    sat
    -0.62
    ebted
    -0.59
    rawdownloadcloneembedreportprint
    -0.59
     represents
    -0.59
     bothers
    -0.59
    POSITIVE LOGITS
     abound
    1.16
     underway
    1.01
     scarce
    0.86
     exchanged
    0.85
     plentiful
    0.84
     flowing
    0.83
     rife
    0.80
    Ĥª
    0.79
    Ĭ±
    0.78
    ģ«
    0.77
    Act Density 0.241%

    No Known Activations