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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating restrictions or limitations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    CHA
    -0.80
    ))))
    -0.74
    });
    -0.73
    imar
    -0.72
    asc
    -0.69
    mir
    -0.67
    enth
    -0.66
    MORE
    -0.64
     syndrome
    -0.64
    ru
    -0.63
    POSITIVE LOGITS
     certain
    0.94
     those
    0.90
     essentials
    0.83
     subsistence
    0.79
     specific
    0.79
     narrow
    0.78
     emergencies
    0.76
     nominal
    0.74
     limited
    0.74
     narrowly
    0.73
    Act Density 0.182%

    No Known Activations