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

    Neuronpedia

    INDEX
    Explanations

    assertive and qualified expressions of opinion or conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elib
    -0.17
     beep
    -0.16
    irie
    -0.15
    earn
    -0.15
    VML
    -0.15
    lush
    -0.15
    estring
    -0.14
    )((((
    -0.14
    lector
    -0.14
    .managed
    -0.14
    POSITIVE LOGITS
     said
    0.23
     say
    0.21
     argument
    0.18
    said
    0.17
     says
    0.16
     saying
    0.16
     regard
    0.16
    .say
    0.16
     argued
    0.15
    say
    0.15
    Act Density 0.170%

    No Known Activations