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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discourse and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by the word "is"

    np_acts-logits-general · gemini-2.0-flash

    discussing abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.75
    EndProject
    -0.64
    DockStyle
    -0.62
    })));
    -0.59
    
    -0.57
    ())))
    -0.57
     AssemblyTitle
    -0.55
    ]));
    -0.55
     betweenstory
    -0.54
    GIVEREF
    -0.54
    POSITIVE LOGITS
     would
    0.60
     is
    0.52
     will
    0.49
     wouldn
    0.47
     shouldn
    0.43
     might
    0.42
     could
    0.42
     seems
    0.40
     isn
    0.40
     may
    0.39
    Act Density 1.682%

    No Known Activations