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

    Neuronpedia

    INDEX
    Explanations

    patterns of repeated hyphens or dashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]}$
    -0.86
    »)
    -0.85
    )».
    -0.84
    ?».
    -0.83
     Barna
    -0.82
    ?»
    -0.82
    ]),
    -0.82
    ]';
    -0.82
    »?
    -0.82
    ReusableCell
    -0.81
    POSITIVE LOGITS
    ----------------
    2.16
    ---------------
    1.38
    --------------
    1.22
    -----------
    1.09
    ------------
    1.08
    -------------
    1.05
    --------
    1.04
    -------
    0.99
    ---------
    0.97
    ------
    0.97
    Act Density 0.201%

    No Known Activations