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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.55
     habituales
    -0.43
     restantes
    -0.43
    :
    -0.42
    .
    -0.42
    Schön
    -0.42
     import
    -0.41
     traseira
    -0.39
    знес
    -0.39
     kysy
    -0.39
    POSITIVE LOGITS
    CodedInputStream
    0.83
     Theſe
    0.80
     '{@
    0.80
     nahilalakip
    0.78
     neceffary
    0.77
     szóci
    0.77
     pleaſure
    0.77
     purpoſe
    0.77
    DOCTYPE
    0.76
     fubject
    0.74
    Act Density 0.292%

    No Known Activations