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

    Neuronpedia

    INDEX
    Explanations

    non-word characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reloaded
    -0.72
     largeDownload
    -0.70
     Closed
    -0.70
     hardened
    -0.69
     widened
    -0.69
     Oswald
    -0.68
     "âĢ¦
    -0.67
     softened
    -0.67
    quished
    -0.66
     Weld
    -0.65
    POSITIVE LOGITS
    window
    1.02
    marriage
    1.02
    wealth
    1.01
    resources
    1.01
    interest
    0.99
    media
    0.99
    collection
    0.98
    party
    0.97
    percent
    0.97
    papers
    0.97
    Act Density 0.031%

    No Known Activations