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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of 'robustness'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rob" and its variations and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jad
    -0.75
     largeDownload
    -0.71
    cape
    -0.68
    alam
    -0.67
     EntityItem
    -0.66
    hips
    -0.64
     VIS
    -0.64
     scratch
    -0.64
    DN
    -0.63
    pai
    -0.62
    POSITIVE LOGITS
    atically
    1.20
    acter
    0.94
    bing
    0.91
    iotics
    0.87
    aceutical
    0.87
    oscopic
    0.87
    ooth
    0.86
    otom
    0.86
    esity
    0.85
    icides
    0.83
    Act Density 0.018%

    No Known Activations