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

    Neuronpedia

    INDEX
    Explanations

    first-person statements and expressions of past experiences or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     not
    -0.17
    FE
    -0.16
     nto
    -0.15
     FE
    -0.15
    令
    -0.14
    gle
    -0.14
    ilo
    -0.14
     neither
    -0.14
    airo
    -0.14
    fe
    -0.13
    POSITIVE LOGITS
    might
    0.20
     might
    0.20
     surely
    0.18
     inv
    0.16
     somehow
    0.16
    SURE
    0.15
    ewis
    0.15
    .addHandler
    0.15
    éĵģ
    0.14
    maybe
    0.14
    Act Density 0.090%

    No Known Activations