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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to repeated actions or routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ays
    -0.17
    linger
    -0.16
    cido
    -0.15
    ovÃŃ
    -0.15
    ux
    -0.15
    oque
    -0.15
    vasive
    -0.14
    ligt
    -0.14
    Äįer
    -0.14
    aten
    -0.13
    POSITIVE LOGITS
     scale
    0.26
     sho
    0.23
    scale
    0.22
     Scale
    0.21
     Sho
    0.21
    Scale
    0.19
     regular
    0.19
     SCALE
    0.18
     whim
    0.18
     mission
    0.18
    Act Density 0.040%

    No Known Activations