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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distinctiveness and separation of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eisen
    -0.15
    .CO
    -0.15
    lope
    -0.14
    ç³»
    -0.14
    åı£
    -0.14
     convenience
    -0.14
    nels
    -0.14
     tern
    -0.14
    etal
    -0.14
     lay
    -0.14
    POSITIVE LOGITS
     separately
    0.19
     separate
    0.18
     Separate
    0.18
    akis
    0.18
     оÑĤделÑĮ
    0.17
    urette
    0.15
    çĭ¬ç«ĭ
    0.15
     isol
    0.15
    589
    0.15
     isolate
    0.14
    Act Density 0.128%

    No Known Activations