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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a similar sentiment or action across different contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     bang
    -0.69
     contrace
    -0.67
    vironment
    -0.62
     routines
    -0.61
     curry
    -0.60
     surrogate
    -0.60
     choir
    -0.56
     synthes
    -0.56
     channels
    -0.56
     covenant
    -0.55
    POSITIVE LOGITS
    IELD
    0.82
    ilton
    0.79
     Berm
    0.73
    ault
    0.70
    blance
    0.69
    ":""},{"
    0.68
    ^^^^
    0.68
    ör
    0.67
    sburgh
    0.67
    });
    0.67
    Act Density 0.128%

    No Known Activations