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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seys
    -0.18
    strup
    -0.15
    HING
    -0.15
    æİĮ
    -0.14
    ourt
    -0.14
     åħ
    -0.14
     éĹ
    -0.14
    Trying
    -0.14
    894
    -0.14
    illas
    -0.14
    POSITIVE LOGITS
     needing
    0.20
     spending
    0.16
     Need
    0.16
     away
    0.16
     back
    0.15
     forever
    0.15
     need
    0.15
     candid
    0.15
    _PB
    0.14
     glad
    0.14
    Act Density 0.058%

    No Known Activations