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

    Neuronpedia

    INDEX
    Explanations

    the phrase "what kind of" followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that categorize or describe types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.68
    arning
    -0.66
    ARY
    -0.62
    YR
    -0.61
    interstitial
    -0.60
    Ļ½
    -0.59
    umsy
    -0.59
     Beir
    -0.58
    VEL
    -0.56
    ģĸ
    -0.54
    POSITIVE LOGITS
     constitutes
    0.78
     havoc
    0.75
     qualifies
    0.74
     awaits
    0.72
    iles
    0.65
     tastes
    0.64
     interests
    0.63
    house
    0.63
    croft
    0.63
     happens
    0.62
    Act Density 0.050%

    No Known Activations