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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and terminologies in the context of advanced theoretical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rust
    -0.15
    GM
    -0.14
     spot
    -0.14
    ilan
    -0.13
    uyu
    -0.13
     GM
    -0.13
     gest
    -0.13
     Estr
    -0.13
    uddy
    -0.13
     Cobb
    -0.13
    POSITIVE LOGITS
    Vir
    0.20
     fusion
    0.19
     Fusion
    0.19
     punct
    0.19
     Vir
    0.19
    fusion
    0.18
    fuse
    0.16
     primaries
    0.16
     Baxter
    0.16
     Åĺ
    0.16
    Act Density 0.154%

    No Known Activations