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

    Neuronpedia

    INDEX
    Explanations

    specific names or titles associated with individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.19
     ..."↵
    -0.17
     ...↵
    -0.17
    âm
    -0.17
     Hispanic
    -0.15
     ...↵↵
    -0.15
     --
    -0.15
    Âĸ
    -0.14
    Âķ
    -0.14
     although
    -0.14
    POSITIVE LOGITS
     Yu
    0.24
    Yu
    0.21
     Mits
    0.20
     Sakura
    0.20
     Yuri
    0.18
     Har
    0.18
     “
    0.17
     Kou
    0.17
     Mitt
    0.16
    InMillis
    0.16
    Act Density 0.005%

    No Known Activations