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

    Neuronpedia

    INDEX
    Explanations

    positive feedback and recommendations for services and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORIZ
    -0.15
    hero
    -0.15
     gridColumn
    -0.14
    ãĥĥãĤ·ãĥ¥
    -0.14
    amic
    -0.14
    ioni
    -0.14
    æ¼
    -0.14
    amburger
    -0.13
    ndon
    -0.13
    _EXPECT
    -0.13
    POSITIVE LOGITS
     repeat
    0.19
     definitely
    0.19
     future
    0.19
     Definitely
    0.18
     Repeat
    0.17
     again
    0.17
     definite
    0.16
    repeat
    0.16
    .future
    0.16
    Repeat
    0.16
    Act Density 0.047%

    No Known Activations