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

    Neuronpedia

    INDEX
    Explanations

    occurrences of closing brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    émon
    -0.67
     Sek
    -0.59
     global
    -0.58
    leſs
    -0.57
     Dol
    -0.55
     Mont
    -0.54
    ρυσ
    -0.54
     GEST
    -0.54
     Wal
    -0.54
    ness
    -0.53
    POSITIVE LOGITS
    ]
    1.95
    ]")]
    1.71
    )]
    1.69
    "]
    1.69
    })]
    1.63
    ']
    1.56
    ])
    1.55
    ″]
    1.55
    ))]
    1.54
    ]
    1.48
    Act Density 0.174%

    No Known Activations