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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    him
    -0.19
     eux
    -0.19
     neither
    -0.18
    arkin
    -0.17
     nowhere
    -0.17
     Neither
    -0.16
    onde
    -0.15
     Them
    -0.15
     gratuits
    -0.15
    Them
    -0.15
    POSITIVE LOGITS
     we
    0.37
     they
    0.32
     you
    0.29
     anyone
    0.24
     it
    0.24
     this
    0.22
     these
    0.22
     he
    0.22
     such
    0.22
    /do
    0.22
    Act Density 0.083%

    No Known Activations