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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data collection

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    RET
    -0.79
    ierre
    -0.64
    otta
    -0.63
    nton
    -0.61
    IFT
    -0.60
    ó
    -0.58
    idth
    -0.58
    coat
    -0.58
    USS
    -0.58
    cipled
    -0.58
    POSITIVE LOGITS
     by
    1.01
     during
    0.96
     BY
    0.94
     therein
    0.91
     outdoors
    0.83
     abroad
    0.82
     herein
    0.82
     throughout
    0.82
     elsewhere
    0.77
     indoors
    0.73
    Act Density 0.180%

    No Known Activations