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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the phrase "seems to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cart
    -0.76
    opens
    -0.75
    ãĤ¦ãĤ¹
    -0.74
    GGGGGGGG
    -0.65
    bats
    -0.63
    edient
    -0.62
     Showdown
    -0.61
    hovah
    -0.60
    lahoma
    -0.60
    ription
    -0.58
    POSITIVE LOGITS
     be
    1.09
     endorse
    1.07
     have
    1.05
     embody
    1.04
     agree
    1.04
     specialize
    1.03
     imply
    1.02
     realise
    1.01
     prefer
    1.00
     possess
    1.00
    Act Density 0.076%

    No Known Activations