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

    Neuronpedia

    INDEX
    Explanations

    web-related terms such as interstitial and content

    oai_token-act-pair · gpt-3.5-turbo

    references to online advertisement formats and their placements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encount
    -0.65
     kicked
    -0.58
     {*
    -0.57
     annually
    -0.56
    :[
    -0.54
     remembered
    -0.54
     recol
    -0.54
     sacked
    -0.53
     proport
    -0.52
     Yamato
    -0.52
    POSITIVE LOGITS
    tnc
    0.87
    MODE
    0.76
    wings
    0.70
    odder
    0.70
    vironment
    0.67
    drm
    0.65
    versions
    0.63
    grain
    0.63
    mes
    0.63
    afety
    0.62
    Act Density 1.052%

    No Known Activations