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

    Neuronpedia

    INDEX
    Explanations

    references to code structure and formatting in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.16
    ãĨ
    -0.15
    ocode
    -0.14
    pcodes
    -0.14
    -highlight
    -0.14
    sted
    -0.14
    -insert
    -0.14
    urbed
    -0.14
    uforia
    -0.13
    ãĥĸãĥŃ
    -0.13
    POSITIVE LOGITS
     separate
    0.20
     empty
    0.19
     dedicate
    0.19
     seperate
    0.19
     simple
    0.19
    FA
    0.18
     dummy
    0.17
    fa
    0.17
     fake
    0.17
     utility
    0.16
    Act Density 0.317%

    No Known Activations