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

    Neuronpedia

    INDEX
    Explanations

    references to grammatical structures involving noun types and usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ado
    -0.15
    DSL
    -0.14
    onaut
    -0.14
    ó
    -0.14
    ivr
    -0.14
    unte
    -0.13
    isode
    -0.13
    ugh
    -0.13
    rosso
    -0.13
    μÎŃ
    -0.13
    POSITIVE LOGITS
     singular
    0.38
     Singular
    0.34
    singular
    0.33
     plural
    0.31
     possess
    0.31
     masculine
    0.29
     animate
    0.28
     sing
    0.27
     gender
    0.25
     neut
    0.25
    Act Density 0.039%

    No Known Activations