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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and related passive constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    allon
    -0.16
    cede
    -0.15
    hide
    -0.15
    unset
    -0.15
    ucas
    -0.14
     frags
    -0.14
     Wohn
    -0.14
    mite
    -0.14
    cly
    -0.14
    POSITIVE LOGITS
     among
    0.19
     involved
    0.18
     next
    0.17
     Among
    0.16
     nearby
    0.16
     another
    0.16
    etak
    0.15
     included
    0.15
     here
    0.15
     meanwhile
    0.14
    Act Density 0.089%

    No Known Activations