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

    Neuronpedia

    INDEX
    Explanations

    financial and economic terminology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ersive
    -0.70
     contam
    -0.64
     surpr
    -0.63
    OGR
    -0.61
    WER
    -0.61
    osate
    -0.59
    ertodd
    -0.59
     condem
    -0.58
     derog
    -0.58
    urer
    -0.57
    POSITIVE LOGITS
     successive
    0.68
     individually
    0.65
     sorts
    0.65
     respective
    0.58
     phases
    0.57
    frames
    0.57
     Georgian
    0.56
     course
    0.56
    ses
    0.55
     Realms
    0.55
    Act Density 9.394%

    No Known Activations