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

    Neuronpedia

    INDEX
    Explanations

    instances of specific Russian morphological constructs and grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cen
    -0.17
    adt
    -0.16
    leur
    -0.16
    isle
    -0.15
     Davidson
    -0.15
    onga
    -0.14
     pub
    -0.14
    ì¼ľ
    -0.14
     Dex
    -0.14
    ufe
    -0.13
    POSITIVE LOGITS
    essler
    0.20
     коÑĢаб
    0.18
     motor
    0.15
    holm
    0.15
     sanit
    0.15
     équip
    0.15
     гÑĢÑĥн
    0.15
     motors
    0.15
     amphib
    0.14
     Motor
    0.14
    Act Density 0.002%

    No Known Activations