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

    Neuronpedia

    INDEX
    Explanations

    expressions of possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meriva
    -0.72
     lamella
    -0.66
     abbildung
    -0.66
    ignoire
    -0.65
     octaves
    -0.64
     betweenstory
    -0.64
     omnia
    -0.63
     jaya
    -0.63
     Hodgkin
    -0.63
    INSEE
    -0.63
    POSITIVE LOGITS
     been
    1.22
     not
    1.12
     gonna
    0.96
     also
    0.95
     really
    0.94
    '])
    0.93
    "])
    0.92
    s
    0.92
     a
    0.91
     is
    0.91
    Act Density 0.199%

    No Known Activations