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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community engagement and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wan
    -0.17
    entity
    -0.15
    iesta
    -0.14
    anta
    -0.14
    kal
    -0.14
    .glob
    -0.13
    _handling
    -0.13
    ffa
    -0.13
    220
    -0.13
    ay
    -0.13
    POSITIVE LOGITS
     via
    0.27
    via
    0.23
     mediante
    0.23
     bằng
    0.21
     through
    0.21
     пÑĥÑĤем
    0.21
     methods
    0.21
    through
    0.21
     Via
    0.21
     طرÛĮÙĤ
    0.20
    Act Density 0.349%

    No Known Activations