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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and related contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃcia
    -0.15
    asso
    -0.15
    oltage
    -0.15
    iant
    -0.15
    esto
    -0.14
    Ãłm
    -0.14
    acco
    -0.14
    è
    -0.14
    olt
    -0.14
    -------------↵
    -0.14
    POSITIVE LOGITS
    aten
    0.21
     ach
    0.21
     xp
    0.21
    iland
    0.20
     xt
    0.20
    jection
    0.20
    ager
    0.20
    asier
    0.20
    aters
    0.20
     vents
    0.19
    Act Density 0.059%

    No Known Activations