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

    Neuronpedia

    INDEX
    Explanations

    future actions or intentions described using the word "will."

    oai_token-act-pair · gpt-3.5-turbo

    future intentions expressed through the word "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bies
    -0.75
    elled
    -0.72
    amped
    -0.66
    REE
    -0.63
    uria
    -0.60
    uman
    -0.60
    Creat
    -0.60
     constituted
    -0.59
    ential
    -0.58
    endar
    -0.58
    POSITIVE LOGITS
     gladly
    1.22
     admit
    1.22
     reiterate
    1.08
     assume
    1.02
     summarize
    1.02
     confess
    0.99
     paraph
    0.99
     explain
    0.98
     presume
    0.97
     concede
    0.95
    Act Density 0.111%

    No Known Activations