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

    Neuronpedia

    INDEX
    Explanations

    uses of the verb "be" in various forms

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ablishment
    -0.63
     residue
    -0.62
     fray
    -0.60
     Tape
    -0.60
    oleon
    -0.60
     Inventory
    -0.60
     unemployment
    -0.60
     infancy
    -0.59
    sonian
    -0.59
     relativity
    -0.58
    POSITIVE LOGITS
    hemoth
    1.31
    arers
    1.19
    acons
    1.17
    heading
    1.16
    ardless
    1.06
    gins
    1.06
    amed
    1.03
    fits
    1.01
    ijing
    1.01
    league
    1.00
    Act Density 0.094%

    No Known Activations