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

    Neuronpedia

    INDEX
    Explanations

    mentions of accomplishments like posts, recordings, and registrations

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to statistical achievements and performances in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.66
    abi
    -0.63
    usb
    -0.62
     lawy
    -0.61
    inventory
    -0.60
    iw
    -0.60
    repre
    -0.59
    laun
    -0.59
     Zionism
    -0.58
    alien
    -0.58
    POSITIVE LOGITS
     impressive
    0.74
     Highest
    0.72
     victories
    0.72
     similarities
    0.69
     highs
    0.69
    interstitial
    0.66
    rued
    0.65
     boasts
    0.64
    -+-+
    0.64
     fewer
    0.64
    Act Density 0.141%

    No Known Activations