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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of 'raising' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to increasing or escalating situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orno
    -0.70
    abase
    -0.68
    zzy
    -0.68
    ennes
    -0.64
    nance
    -0.61
    uds
    -0.60
     Siem
    -0.60
    ime
    -0.59
    lon
    -0.59
     Atlantis
    -0.59
    POSITIVE LOGITS
     raising
    3.47
     raise
    2.23
    raising
    2.16
     raised
    1.96
     lowering
    1.91
     raises
    1.75
     Raise
    1.67
    raise
    1.50
    raised
    1.45
     boosting
    1.38
    Act Density 0.010%

    No Known Activations