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

    Neuronpedia

    INDEX
    Explanations

    themes centered around community engagement and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YSIS
    -0.15
    CTR
    -0.14
    enas
    -0.14
    _SANITIZE
    -0.13
    .Dot
    -0.13
    ungen
    -0.13
     Baum
    -0.13
    HasBeen
    -0.13
    æĿ¿
    -0.13
    OTO
    -0.13
    POSITIVE LOGITS
     participation
    0.17
     Participation
    0.16
     代
    0.14
    åıĤä¸İ
    0.14
    -feedback
    0.14
     particip
    0.14
    rots
    0.14
     öz
    0.14
    .self
    0.14
     input
    0.14
    Act Density 0.322%

    No Known Activations