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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to specific events or historical facts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" in various contexts within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reperto
    -0.71
     showc
    -0.60
    NetMessage
    -0.59
     misunder
    -0.58
    wcs
    -0.57
     ingred
    -0.53
     mathemat
    -0.53
    ashtra
    -0.53
     abund
    -0.52
     privile
    -0.52
    POSITIVE LOGITS
     course
    0.93
     sorts
    0.80
    course
    0.75
    icial
    0.74
     ours
    0.55
     Nanto
    0.51
    Hope
    0.51
    loaded
    0.50
     Friendship
    0.49
     Nations
    0.48
    Act Density 0.989%

    No Known Activations