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

    Neuronpedia

    INDEX
    Explanations

    names and references related to a specific entity or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.95
     Rowley
    -0.95
     Alembic
    -0.83
     Sava
    -0.80
    ebp
    -0.71
    stridium
    -0.71
    aragua
    -0.70
     consec
    -0.70
    Anil
    -0.70
     Arag
    -0.69
    POSITIVE LOGITS
     Gos
    0.81
    izers
    0.76
    ฉ
    0.76
    ⓧ
    0.75
    zad
    0.75
     ordonn
    0.74
    łach
    0.74
    ebel
    0.73
     exerting
    0.73
    izr
    0.73
    Act Density 0.711%

    No Known Activations