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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to be" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adden
    -0.17
    RefPtr
    -0.15
     hasn
    -0.15
    ndon
    -0.15
     doesn
    -0.14
    never
    -0.14
    nowledge
    -0.14
    orda
    -0.14
    eldom
    -0.14
     never
    -0.13
    POSITIVE LOGITS
     need
    0.30
     hell
    0.29
     bed
    0.28
     be
    0.28
     war
    0.27
     jail
    0.27
     extremes
    0.27
     Hell
    0.25
     heaven
    0.24
     town
    0.24
    Act Density 0.053%

    No Known Activations