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

    Neuronpedia

    INDEX
    Explanations

    words related to lifting or raising

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of lifting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ually
    -0.87
    stown
    -0.81
    mond
    -0.71
    perate
    -0.68
    Dialogue
    -0.67
    vironment
    -0.67
    ual
    -0.66
    ified
    -0.65
     Palin
    -0.65
    alist
    -0.65
    POSITIVE LOGITS
    lift
    1.15
    lifting
    0.93
     lift
    0.91
     Lift
    0.85
    ĸļ
    0.83
     lifting
    0.80
    rers
    0.78
    houses
    0.77
     lifts
    0.77
     weights
    0.75
    Act Density 0.036%

    No Known Activations