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

    Neuronpedia

    INDEX
    Explanations

    references to notable actions, identities, or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLU
    -0.17
    arris
    -0.15
    CLUD
    -0.15
    bor
    -0.14
    ogan
    -0.14
    бина
    -0.14
    encer
    -0.14
    ÙģÙĪ
    -0.14
    berger
    -0.14
    ield
    -0.14
    POSITIVE LOGITS
    appa
    0.15
    umbnails
    0.14
    resse
    0.14
     Clar
    0.14
    -ob
    0.13
    oplayer
    0.13
    432
    0.13
    λια
    0.13
     Alb
    0.13
     Bib
    0.13
    Act Density 0.002%

    No Known Activations