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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration and global efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crawford
    -0.14
    _dummy
    -0.14
    ollapse
    -0.14
     Briggs
    -0.13
    ursal
    -0.13
    맨
    -0.13
     Norris
    -0.13
    ses
    -0.13
    etten
    -0.13
    BR
    -0.13
    POSITIVE LOGITS
    indow
    0.15
     INLINE
    0.15
    chod
    0.14
    ëłĪìĬ¤
    0.13
    ãĥķãĥ¬
    0.13
    isay
    0.13
     Wax
    0.13
    èĺ
    0.13
    .sax
    0.13
    ché
    0.13
    Act Density 0.066%

    No Known Activations