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

    Neuronpedia

    INDEX
    Explanations

    references to socioeconomic and political hierarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     useDispatch
    -0.52
    perror
    -0.46
     Day
    -0.46
    numerusform
    -0.46
     Aspect
    -0.44
    gamento
    -0.44
     Week
    -0.43
     medži
    -0.42
     Way
    -0.41
    brainer
    -0.41
    POSITIVE LOGITS
     ranks
    1.36
     rung
    1.21
     rank
    1.19
     eche
    1.19
     ladder
    1.16
     rankings
    1.14
     tier
    1.12
     Ranks
    1.10
     tiers
    1.08
    ranks
    1.05
    Act Density 0.350%

    No Known Activations