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

    Neuronpedia

    INDEX
    Explanations

    contextual indicators of relationships or references within textual passages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andExpect
    -0.66
    aimana
    -0.61
     autorytatywna
    -0.56
    ArgumentParser
    -0.51
     quite
    -0.50
    ORGE
    -0.50
     חיצוניים
    -0.50
     dataSnapshot
    -0.49
    ammen
    -0.48
    ┬
    -0.48
    POSITIVE LOGITS
     Majefty
    1.09
     Shakspeare
    1.05
     myſelf
    1.04
     Efq
    1.03
     Houſe
    1.01
     Jefus
    1.00
     Monfieur
    0.99
     himſelf
    0.99
    ſelf
    0.95
     itſelf
    0.94
    Act Density 0.250%

    No Known Activations