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

    Neuronpedia

    INDEX
    Explanations

    specific references or citations in academic or research documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koz
    -0.99
    CascadeType
    -0.86
     rhestr
    -0.79
    ufact
    -0.77
    Koz
    -0.77
    lessed
    -0.76
     لينك
    -0.75
    ressee
    -0.74
     plant
    -0.73
     Humid
    -0.73
    POSITIVE LOGITS
    </sup>
    1.60
    </sub>
    1.46
    </u>
    1.31
    </s>
    1.27
    </em>
    1.09
    </i>
    1.03
    </code>
    0.99
     }}
    0.96
    }}
    0.87
    〕
    0.86
    Act Density 0.152%

    No Known Activations