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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    s
    -0.85
    zustellen
    -0.71
     is
    -0.70
    éos
    -0.69
     the
    -0.64
     Griffin
    -0.63
    ingles
    -0.63
    chts
    -0.62
    unas
    -0.62
     Nar
    -0.62
    POSITIVE LOGITS
     Rave
    0.85
     ModelExpression
    0.82
     myſelf
    0.80
     Houſe
    0.78
     Amadeus
    0.77
     ſtand
    0.76
     doInBackground
    0.75
     témoins
    0.75
     Lave
    0.74
    Hav
    0.73
    Act Density 0.013%

    No Known Activations