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

    Neuronpedia

    INDEX
    Explanations

    non-standard punctuation and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    хьтан
    -0.70
     Hirst
    -0.65
     fest
    -0.64
    ponent
    -0.64
     color
    -0.64
    ষ্
    -0.62
     Koc
    -0.61
     resolver
    -0.61
     Zab
    -0.60
    aleb
    -0.59
    POSITIVE LOGITS
    </blockquote>
    2.24
    \]
    1.36
    </h1>
    1.27
    ')";
    1.24
    }\]
    1.23
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.21
    </h5>
    1.21
    }}],
    1.19
    </h6>
    1.18
    }")]
    1.17
    Act Density 0.009%

    No Known Activations