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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific occurrences or instances

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    dale
    -0.73
    uminati
    -0.72
    inki
    -0.68
    arts
    -0.67
    depend
    -0.66
    iculture
    -0.66
    ement
    -0.64
    ãģį
    -0.62
    rake
    -0.61
    below
    -0.61
    POSITIVE LOGITS
     anyone
    0.78
     someone
    0.77
     they
    0.74
     since
    0.73
     foreigners
    0.73
    eve
    0.73
     that
    0.71
    ndra
    0.70
     she
    0.68
     we
    0.67
    Act Density 0.036%

    No Known Activations