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

    Neuronpedia

    INDEX
    Explanations

    mentions of financial matters or instructions/documents in an informative context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    OGR
    -0.72
    ilts
    -0.66
    OSP
    -0.61
     Forums
    -0.61
    Dialogue
    -0.60
    Pos
    -0.58
    Twe
    -0.56
    members
    -0.56
    Others
    -0.56
    Eastern
    -0.55
    POSITIVE LOGITS
     yourselves
    0.90
     yourself
    0.88
    Tube
    0.74
     shalt
    0.73
     need
    0.72
     mileage
    0.70
     gotta
    0.67
    cale
    0.66
    lly
    0.64
     guessed
    0.62
    Act Density 12.057%

    No Known Activations