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

    Neuronpedia

    INDEX
    Explanations

    emphasizing or referencing repeated phrases, particularly with the word "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rsiniz
    -0.73
    INSEE
    -0.71
     Hamlin
    -0.68
    kém
    -0.66
    detectChanges
    -0.65
     cair
    -0.64
    ignoire
    -0.63
     Hati
    -0.63
    izare
    -0.62
    chläge
    -0.62
    POSITIVE LOGITS
     been
    1.04
    s
    0.91
     gotta
    0.89
     gonna
    0.88
    érrez
    0.83
     تانيه
    0.82
    been
    0.80
    󠁿
    0.79
     youre
    0.76
     kids
    0.75
    Act Density 0.259%

    No Known Activations