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

    Neuronpedia

    INDEX
    Explanations

    descriptions of specific events involving people, actions, and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of actions involving groups of people or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bnb
    -0.66
    cipled
    -0.61
    ãĥĥãĥī
    -0.58
     survives
    -0.58
    zsche
    -0.58
    unker
    -0.57
     sooner
    -0.56
    ahime
    -0.56
    ãĤ¦ãĤ¹
    -0.55
     Helpful
    -0.55
    POSITIVE LOGITS
     nearby
    0.67
    interstitial
    0.66
     renov
    0.62
     Ramadan
    0.60
     ostensibly
    0.59
    ologne
    0.59
    .[
    0.58
     renovations
    0.58
     supposedly
    0.57
     filming
    0.56
    Act Density 1.024%

    No Known Activations