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

    Neuronpedia

    INDEX
    Explanations

    sentences related to the absence or lack of specific information or details

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or absence of information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newsletters
    -0.73
    arta
    -0.68
     gigs
    -0.65
    vernment
    -0.65
    fighting
    -0.63
     Serving
    -0.62
     Enemies
    -0.61
     legions
    -0.60
    arms
    -0.60
     generations
    -0.60
    POSITIVE LOGITS
    hes
    1.28
     omitted
    1.14
     removed
    1.12
     withdrawn
    1.04
     subsequently
    1.01
     chosen
    1.01
     deemed
    0.99
     discovered
    0.99
     originally
    0.98
     cancelled
    0.98
    Act Density 0.227%

    No Known Activations