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

    Neuronpedia

    INDEX
    Explanations

    phrases denoting superlatives or extremes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayne
    -0.16
    teÅŁ
    -0.16
    ays
    -0.15
    odesk
    -0.14
    AYS
    -0.14
    fy
    -0.13
     ._
    -0.13
    assel
    -0.13
    alent
    -0.13
    aji
    -0.13
    POSITIVE LOGITS
     talked
    0.25
    -talk
    0.23
     recogn
    0.20
     loved
    0.20
     successful
    0.20
     famous
    0.19
    ansi
    0.19
     respected
    0.19
    recogn
    0.19
    èijĹ
    0.18
    Act Density 0.068%

    No Known Activations