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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or going back to previous places or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alt
    -0.18
    ä¹ĭä¸Ģ
    -0.16
    eng
    -0.14
     Fres
    -0.14
    hs
    -0.14
    wald
    -0.13
    _ALT
    -0.13
    et
    -0.13
    oyal
    -0.13
    ģ
    -0.13
    POSITIVE LOGITS
    ijkstra
    0.20
     lại
    0.17
    celik
    0.16
    sWith
    0.15
     again
    0.15
    dings
    0.15
    اجÙĩ
    0.15
    ró
    0.15
    dialogs
    0.14
    .si
    0.14
    Act Density 0.049%

    No Known Activations