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

    Neuronpedia

    INDEX
    Explanations

    web links in strings of text

    oai_token-act-pair · gpt-3.5-turbo

    URLs and internet-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     backlog
    -0.52
     evac
    -0.45
     shelters
    -0.45
     trenches
    -0.45
     noisy
    -0.44
     manufactures
    -0.43
     pans
    -0.43
     GI
    -0.42
     subsid
    -0.42
     shelter
    -0.42
    POSITIVE LOGITS
    his
    0.86
    His
    0.82
     himself
    0.76
     his
    0.72
     HIS
    0.71
    çĶ°
    0.66
     His
    0.66
     Himself
    0.65
    He
    0.65
    him
    0.64
    Act Density 2.403%

    No Known Activations