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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isk
    -0.54
    itz
    -0.54
    HasIndex
    -0.53
    illips
    -0.51
    fils
    -0.51
    ing
    -0.50
    iness
    -0.50
    is
    -0.50
     x
    -0.50
    itself
    -0.49
    POSITIVE LOGITS
     are
    0.78
     were
    0.72
    were
    0.67
     Were
    0.66
     voltak
    0.64
    Are
    0.63
     eivät
    0.62
    Were
    0.62
     były
    0.60
     mereka
    0.59
    Act Density 0.541%

    No Known Activations