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

    Neuronpedia

    INDEX
    Explanations

    examples of sentences where words or phrases convey uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility or conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.67
     Entered
    -0.66
     Meter
    -0.63
     tabl
    -0.60
     Mayer
    -0.60
     Koen
    -0.59
     Jess
    -0.59
     Pog
    -0.57
     lb
    -0.56
     Lu
    -0.56
    POSITIVE LOGITS
    theless
    1.73
    etheless
    1.59
    selves
    1.41
    terday
    1.38
    usterity
    1.28
    ecd
    1.27
    withstanding
    1.21
    mosp
    1.21
    self
    1.13
    tenance
    1.11
    Act Density 0.255%

    No Known Activations