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

    Neuronpedia

    INDEX
    Explanations

    references to rankings or placements in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dere
    -0.17
     Sesso
    -0.16
    .Router
    -0.15
    ãĥ³ãĥ
    -0.15
    nt
    -0.14
    ega
    -0.14
     Hind
    -0.14
    ãĥ³ãĥĶ
    -0.14
    iplina
    -0.14
    nge
    -0.14
    POSITIVE LOGITS
    ienes
    0.14
    omas
    0.14
    ichen
    0.14
    ibox
    0.14
    veyor
    0.13
    itsu
    0.13
     erre
    0.13
     î¡
    0.13
    pron
    0.13
    yang
    0.13
    Act Density 0.061%

    No Known Activations