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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koz
    -0.93
    ^(@)
    -0.89
     لينك
    -0.89
     rhestr
    -0.87
    leſs
    -0.86
     ISD
    -0.86
    databind
    -0.85
    CascadeType
    -0.83
    ressee
    -0.82
    LikeLiked
    -0.81
    POSITIVE LOGITS
    </sup>
    1.44
    </sub>
    1.26
    </u>
    1.21
    </s>
    1.01
    </em>
    1.00
    </code>
    0.88
    </i>
    0.87
    }}
    0.86
    ))
    0.85
    </strong>
    0.83
    Act Density 0.173%

    No Known Activations