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

    Neuronpedia

    INDEX
    Explanations

    words related to strength and connections, such as 'formed', 'force', 'connected', 'service', and 'together'

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events or changes in status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.51
     opio
    -0.45
     Vaugh
    -0.45
     Kardash
    -0.42
     advoc
    -0.40
     Seym
    -0.39
    schild
    -0.39
    ãĤ¦ãĤ¹
    -0.39
    umbn
    -0.39
    abc
    -0.39
    POSITIVE LOGITS
     thence
    0.48
     largeDownload
    0.46
     unto
    0.45
     âĵĺ
    0.44
    )?
    0.43
    cession
    0.43
     secondly
    0.43
     proceeded
    0.43
     :=
    0.42
     arrived
    0.42
    Act Density 1.581%

    No Known Activations