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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to emotional and social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']);
    -0.71
    ()))
    -0.70
     });
    -0.69
    "));
    -0.69
     ReactDOM
    -0.68
    ])
    -0.68
    ")){
    -0.66
     })
    -0.66
    ]){
    -0.65
    σιμοποι
    -0.62
    POSITIVE LOGITS
     attitude
    1.92
     attitudes
    1.78
     atmosphere
    1.73
    attitude
    1.70
     Attitude
    1.70
     Attitudes
    1.65
     Atmosphere
    1.56
    Attitude
    1.54
    atmosphere
    1.50
     atmospheres
    1.45
    Act Density 0.129%

    No Known Activations