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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating desires or intentions to do something specific

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express desires or intended actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peaks
    -0.76
    furt
    -0.74
    river
    -0.67
     ceased
    -0.67
    quickShipAvailable
    -0.66
    grounds
    -0.66
     Lenn
    -0.63
    mount
    -0.61
    cephal
    -0.60
     Flex
    -0.60
    POSITIVE LOGITS
     accomplish
    1.08
     achieve
    0.92
     maximize
    0.87
     tackle
    0.86
     earn
    0.85
     pursue
    0.83
     do
    0.83
     improve
    0.82
     pray
    0.81
     perform
    0.80
    Act Density 0.172%

    No Known Activations