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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to objects or technologies being thin or slim

    oai_token-act-pair · gpt-3.5-turbo

    references to thinness and slimness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.78
    OUP
    -0.67
     behav
    -0.66
     Quake
    -0.66
    OUN
    -0.65
     citation
    -0.64
    ADRA
    -0.63
     loudly
    -0.62
    eering
    -0.60
    bucks
    -0.59
    POSITIVE LOGITS
    ned
    1.39
    ning
    1.21
    ners
    1.02
    med
    0.95
    ming
    0.94
    nery
    0.81
     margins
    0.80
     (<
    0.79
    ware
    0.76
    skinned
    0.75
    Act Density 0.065%

    No Known Activations