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

    Neuronpedia

    INDEX
    Explanations

    coordinating conjunctions and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     they
    -0.18
    they
    -0.16
    gger
    -0.15
    æ
    -0.15
     {}.
    -0.14
     maka
    -0.14
    åŃIJãģ¯
    -0.14
    oord
    -0.14
    asta
    -0.13
    earer
    -0.13
    POSITIVE LOGITS
     because
    0.21
     given
    0.20
     despite
    0.20
     subsequent
    0.20
     knowing
    0.20
     thanks
    0.19
     with
    0.19
     after
    0.19
     considering
    0.19
     contrary
    0.18
    Act Density 0.100%

    No Known Activations