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

    Neuronpedia

    INDEX
    Explanations

    clauses that express opinions or concerns related to political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     she
    -1.26
     his
    -1.20
     this
    -1.20
     her
    -1.20
     our
    -1.17
     then
    -1.09
     here
    -1.07
     now
    -1.07
     these
    -1.06
     their
    -1.04
    POSITIVE LOGITS
     The
    1.12
     This
    1.08
     There
    1.05
     It
    1.05
     They
    0.99
     These
    0.97
     If
    0.95
     That
    0.94
     However
    0.90
     When
    0.89
    Act Density 2.476%

    No Known Activations