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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns and conjunctions that help create clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahl
    -0.18
    amik
    -0.16
     Äijiá»ĥn
    -0.15
    매
    -0.14
    ennie
    -0.14
    ignite
    -0.14
    831
    -0.14
    +xml
    -0.14
    âĢ¦↵↵↵
    -0.14
     pisc
    -0.14
    POSITIVE LOGITS
    upon
    0.16
     defaults
    0.15
     Latter
    0.15
    à¤Łà¤°
    0.14
    onto
    0.14
    odes
    0.14
     consenting
    0.14
    ropolis
    0.14
    olas
    0.14
     Boris
    0.13
    Act Density 0.162%

    No Known Activations