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

    Neuronpedia

    INDEX
    Explanations

    code-related instructions and concepts.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz
    New Auto-Interp
    Negative Logits
    :
    0.22
    =
    0.20
    \
    0.20
     fished
    0.18
    ın
    0.17
     metabolized
    0.17
     oth
    0.17
     removing
    0.17
     također
    0.17
     descended
    0.17
    POSITIVE LOGITS
     iteration
    0.21
     dilemma
    0.19
     masterpiece
    0.19
     predicament
    0.18
     edifice
    0.17
    라면
    0.17
     모습
    0.16
     regimen
    0.16
    Homework
    0.16
     idea
    0.15
    Act Density 1.318%

    No Known Activations