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

    Neuronpedia

    INDEX
    Explanations

    short phrases containing the word "but"

    oai_token-act-pair · gpt-3.5-turbo

    the conjunctions "and" and "but" used to connect phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irm
    -0.67
    root
    -0.64
    >[
    -0.64
    otine
    -0.63
    rouse
    -0.61
    ail
    -0.59
     Include
    -0.58
    rift
    -0.58
    luster
    -0.58
    igate
    -0.58
    POSITIVE LOGITS
     spends
    1.21
     remembers
    1.20
     prefers
    1.15
     enjoys
    1.15
     believes
    1.10
     underwent
    1.09
     spent
    1.07
     thinks
    1.07
     loves
    1.07
     was
    1.07
    Act Density 0.230%

    No Known Activations