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

    Neuronpedia

    INDEX
    Explanations

    future events or plans

    oai_token-act-pair · gpt-3.5-turbo

    the word "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.74
     Stain
    -0.66
    pedia
    -0.66
     Moose
    -0.65
    vas
    -0.64
     partName
    -0.63
    oso
    -0.61
     Hes
    -0.61
     Newspaper
    -0.61
     Lines
    -0.60
    POSITIVE LOGITS
     replaced
    1.06
     able
    0.96
    heading
    0.96
     evaluated
    0.95
    ige
    0.95
     considered
    0.92
     judged
    0.92
     released
    0.92
     seen
    0.90
     phased
    0.88
    Act Density 0.072%

    No Known Activations