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

    Neuronpedia

    INDEX
    Explanations

    references to episodes, interviews, or articles in media discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     but
    -0.17
     and
    -0.17
    but
    -0.17
     hers
    -0.15
    ä¸Ķ
    -0.14
     or
    -0.14
    and
    -0.14
    them
    -0.14
    	and
    -0.14
     него
    -0.14
    POSITIVE LOGITS
     titled
    0.39
     entitled
    0.36
     dated
    0.28
     published
    0.27
     which
    0.27
     we
    0.27
     released
    0.26
    itled
    0.25
     posted
    0.24
     conducted
    0.24
    Act Density 0.129%

    No Known Activations