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

    Neuronpedia

    INDEX
    Explanations

    references to "rew" and "dow" concepts, which may relate to rewards and dowry discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uously
    -0.79
    uous
    -0.70
    ually
    -0.69
     otherwise
    -0.69
     athlet
    -0.64
     suspic
    -0.63
    âĸ¬âĸ¬
    -0.63
     Franch
    -0.61
    ãĥĩ
    -0.61
     Imran
    -0.60
    POSITIVE LOGITS
    ritten
    1.38
    ards
    1.20
    atche
    1.15
    riter
    1.12
    arded
    1.07
    rites
    1.03
    arding
    1.00
    rote
    1.00
    rite
    0.99
    atcher
    0.94
    Act Density 0.007%

    No Known Activations