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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions indicating relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igar
    -0.15
     Overall
    -0.15
    etas
    -0.15
    аÑĤкÑĥ
    -0.15
    borough
    -0.14
     Nun
    -0.14
    ritte
    -0.14
    lush
    -0.14
    699
    -0.14
    mina
    -0.14
    POSITIVE LOGITS
    ÑĭÑĪ
    0.15
     alike
    0.15
    ollipop
    0.15
    aid
    0.14
    ooks
    0.14
    agan
    0.14
    annis
    0.14
    IAN
    0.14
    intern
    0.14
    IDI
    0.13
    Act Density 0.100%

    No Known Activations