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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTES
    -0.16
    pu
    -0.15
     Rud
    -0.14
     Rust
    -0.14
     Bounty
    -0.14
     Ramsey
    -0.14
    LineNumber
    -0.14
     rust
    -0.14
     Fitness
    -0.14
     NOM
    -0.14
    POSITIVE LOGITS
    associ
    0.27
     Hop
    0.25
     associative
    0.24
     coal
    0.24
    Hop
    0.23
    Associ
    0.22
     Swe
    0.22
     Coal
    0.21
    bial
    0.20
     Lie
    0.20
    Act Density 0.030%

    No Known Activations