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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or relationship descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.17
     somehow
    -0.17
    remely
    -0.17
     absolutely
    -0.16
    chg
    -0.16
    orie
    -0.15
    еÑĢÑĪ
    -0.15
     suche
    -0.15
     seemingly
    -0.14
    such
    -0.14
    POSITIVE LOGITS
    -sort
    0.25
     like
    0.21
     Like
    0.18
    /s
    0.16
     LIKE
    0.16
    -ÑĤаки
    0.16
    antity
    0.16
    Like
    0.14
    isos
    0.14
    lesh
    0.14
    Act Density 0.035%

    No Known Activations