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

    Neuronpedia

    INDEX
    Explanations

    instances of specific actions or events in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" indicating existence or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lack
    -0.69
    PsyNetMessage
    -0.68
     Extend
    -0.66
     @@
    -0.63
     Outer
    -0.63
     Current
    -0.62
     Include
    -0.61
     Wyr
    -0.61
     Conditions
    -0.59
     Caucasus
    -0.59
    POSITIVE LOGITS
     greeted
    1.19
     confronted
    1.13
     rewarded
    1.13
     able
    1.10
    hes
    1.10
     promptly
    1.09
     escorted
    1.07
     ushered
    1.03
     startled
    1.02
     astonished
    1.01
    Act Density 0.190%

    No Known Activations