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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ownership or possession as well as values or amounts expressed in monetary terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    matter
    -0.35
     directions
    -0.34
    ileaks
    -0.34
    enegger
    -0.34
     situation
    -0.32
    worm
    -0.31
    scan
    -0.31
    NN
    -0.31
    aleigh
    -0.30
    jc
    -0.30
    POSITIVE LOGITS
     excellence
    0.48
     secrecy
    0.45
     honour
    0.43
     reverence
    0.43
     accomplishment
    0.42
     sanct
    0.42
     honor
    0.42
     virtues
    0.42
     praise
    0.42
     esteem
    0.42
    Act Density 14.870%

    No Known Activations