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

    Neuronpedia

    INDEX
    Explanations

    references to office spaces and real estate developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oise
    -0.90
    theless
    -0.81
    MQ
    -0.72
    âķIJâķIJ
    -0.72
    olini
    -0.71
    ï¸
    -0.70
    ebook
    -0.69
    ivals
    -0.68
     Haram
    -0.68
    cible
    -0.66
    POSITIVE LOGITS
    holder
    1.11
    holders
    1.09
    tops
    1.02
    room
    0.91
     holder
    0.85
    person
    0.82
    wife
    0.81
     365
    0.80
     tower
    0.78
     suite
    0.78
    Act Density 0.023%

    No Known Activations