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

    Neuronpedia

    INDEX
    Explanations

    verbs in the past tense indicating completion or future intention

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.65
    tery
    -0.64
    maxwell
    -0.60
     Percentage
    -0.59
    ¶
    -0.58
    CTV
    -0.57
    {
    -0.56
    river
    -0.56
    scientific
    -0.55
    /+
    -0.54
    POSITIVE LOGITS
     be
    2.40
     Be
    1.43
    Be
    1.37
     BE
    1.33
    be
    1.30
     become
    0.98
     beet
    0.95
     been
    0.91
     remain
    0.91
     go
    0.90
    Act Density 0.254%

    No Known Activations