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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions indicating options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    403
    -0.15
     ones
    -0.15
    966
    -0.15
     caps
    -0.14
    yc
    -0.14
    683
    -0.14
    é®
    -0.14
    762
    -0.13
    umbo
    -0.13
     ки
    -0.13
    POSITIVE LOGITS
     couple
    0.19
    (s
    0.19
     pair
    0.17
     two
    0.16
     piece
    0.16
     series
    0.16
     sebuah
    0.15
     several
    0.15
     somebody
    0.15
     someone
    0.15
    Act Density 0.193%

    No Known Activations