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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate findings and results from studies or research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dost
    -0.15
    çŁ¢
    -0.14
    .debian
    -0.14
    .SDK
    -0.13
    οÏħÏĥ
    -0.13
    åı²
    -0.13
     THEIR
    -0.13
     segundo
    -0.13
    ritable
    -0.13
     Jens
    -0.13
    POSITIVE LOGITS
     that
    0.21
     evidence
    0.20
     promise
    0.17
     no
    0.17
     bahwa
    0.16
     clear
    0.16
     little
    0.15
     marked
    0.15
     rằng
    0.15
    agan
    0.15
    Act Density 0.084%

    No Known Activations