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

    Neuronpedia

    INDEX
    Explanations

    phrases related to asserting opinions forcefully

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements challenging misconceptions or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukong
    -0.80
    knit
    -0.71
    chron
    -0.69
    figured
    -0.66
    iverpool
    -0.63
     Nurs
    -0.62
     Elliot
    -0.60
    anchester
    -0.60
    encers
    -0.59
    encer
    -0.59
    POSITIVE LOGITS
     unworthy
    1.00
     unacceptable
    0.99
     folly
    0.96
     irresponsible
    0.95
     foolish
    0.93
     heresy
    0.93
     counterproductive
    0.92
     futile
    0.90
     dishon
    0.88
     invalid
    0.86
    Act Density 0.440%

    No Known Activations