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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -1.41
    principalColumn
    -1.05
    mybatisplus
    -0.99
    Попис
    -0.98
    NUMX
    -0.96
     pinulongan
    -0.96
     تانيه
    -0.94
    ImageContext
    -0.93
    AnchorStyles
    -0.91
     ivelany
    -0.88
    POSITIVE LOGITS
    ↵↵
    0.75
    The
    0.54
        
    0.53
    This
    0.52
    (
    0.49
    ↵
    0.48
    //
    0.47
                
    0.46
    We
    0.46
            
    0.45
    Act Density 1.638%

    No Known Activations