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

    Neuronpedia

    INDEX
    Explanations

    past tense forms of the verb "to be" and related inflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unk
    -0.16
    ampil
    -0.15
    istributed
    -0.15
     UNKNOWN
    -0.14
     sobie
    -0.14
    agina
    -0.14
    ailable
    -0.14
     encount
    -0.14
    íĴĪ
    -0.14
     glyphicon
    -0.14
    POSITIVE LOGITS
     chosen
    0.32
     chose
    0.28
     decided
    0.28
     choose
    0.27
     choosing
    0.26
    chosen
    0.25
     Choose
    0.24
     selected
    0.24
     choice
    0.23
    Choose
    0.22
    Act Density 0.008%

    No Known Activations