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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enabling actions or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scribed
    -0.16
    elves
    -0.15
    yt
    -0.15
    rani
    -0.15
    kar
    -0.15
    uten
    -0.14
    ivos
    -0.14
    builders
    -0.14
    дап
    -0.13
    eme
    -0.13
    POSITIVE LOGITS
     us
    0.18
    fullscreen
    0.14
    łģ
    0.14
    aby
    0.13
     Controlled
    0.13
    ãĤĮãģ©
    0.13
    SingleNode
    0.13
    adian
    0.13
     Lehr
    0.13
    /dis
    0.13
    Act Density 0.045%

    No Known Activations