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

    Neuronpedia

    INDEX
    Explanations

    words related to physical stains or tarnishing

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with stains and tarnishing of reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WER
    -0.74
    entric
    -0.73
    trak
    -0.72
    ctrl
    -0.72
    entary
    -0.72
    odcast
    -0.65
    ommod
    -0.65
    essing
    -0.65
    Vs
    -0.64
    OTAL
    -0.63
    POSITIVE LOGITS
     tarn
    1.10
     stain
    1.03
     stained
    1.02
    red
    1.00
     tint
    0.90
    luster
    0.88
     stains
    0.87
     dye
    0.80
    stained
    0.79
    prints
    0.79
    Act Density 0.030%

    No Known Activations