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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the removal of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "removed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.72
    idth
    -0.66
    ebus
    -0.59
    akening
    -0.58
    ingham
    -0.58
    SON
    -0.57
    emate
    -0.57
    enegger
    -0.56
    orum
    -0.56
    ramid
    -0.55
    POSITIVE LOGITS
     from
    1.18
     altogether
    0.97
     surg
    0.95
    from
    0.94
     FROM
    0.90
     entirely
    0.85
     From
    0.76
    frog
    0.75
     abruptly
    0.73
     outright
    0.70
    Act Density 0.079%

    No Known Activations