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

    Neuronpedia

    INDEX
    Explanations

    past tense forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    innen
    -0.16
    oyer
    -0.15
    ContextHolder
    -0.15
    another
    -0.15
    atha
    -0.14
    ener
    -0.14
    ynom
    -0.14
    dna
    -0.14
    enek
    -0.14
    ekl
    -0.13
    POSITIVE LOGITS
     head
    0.23
     chief
    0.21
     editor
    0.21
     owner
    0.20
     president
    0.20
     involved
    0.18
     lead
    0.18
     employed
    0.18
     chairman
    0.17
     vice
    0.17
    Act Density 0.097%

    No Known Activations