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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lifting actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to raising or elevating something, often in a metaphorical or literal sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errilla
    -0.70
     Palin
    -0.68
    tex
    -0.67
    ãĥ£
    -0.65
    ño
    -0.65
    Cola
    -0.64
    TAG
    -0.64
    915
    -0.63
    perate
    -0.62
    Pope
    -0.62
    POSITIVE LOGITS
     weights
    1.15
     lift
    0.99
     lifting
    0.98
    lift
    0.98
     lifted
    0.91
     Lift
    0.84
    weight
    0.83
     lifts
    0.82
    dogs
    0.79
     embargo
    0.76
    Act Density 0.034%

    No Known Activations