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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the prediction of future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating anticipation or expectation of future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hovah
    -0.66
    anwhile
    -0.62
    mite
    -0.58
     Appears
    -0.56
    cyclopedia
    -0.55
    */(
    -0.54
    requires
    -0.54
     ensures
    -0.54
     sits
    -0.53
     retains
    -0.52
    POSITIVE LOGITS
     sooner
    0.66
     someday
    0.64
     hadn
    0.63
     impending
    0.59
     Voldemort
    0.56
     imminent
    0.55
     Coil
    0.52
     belonged
    0.51
    ranged
    0.50
     Dumbledore
    0.49
    Act Density 1.660%

    No Known Activations