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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and demands

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating expectations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iard
    -0.73
    ksh
    -0.67
    ourgeois
    -0.66
    oi
    -0.66
     Heads
    -0.65
    eteenth
    -0.64
     differe
    -0.62
     Levels
    -0.62
    igr
    -0.62
    ewater
    -0.62
    POSITIVE LOGITS
     expectation
    1.11
     desire
    1.05
     crave
    1.02
     obligation
    0.99
     desires
    0.94
     hoped
    0.94
     expect
    0.92
    isSpecialOrderable
    0.92
     expecting
    0.90
     longing
    0.90
    Act Density 0.143%

    No Known Activations