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

    Neuronpedia

    INDEX
    Explanations

    differences or comparisons between different entities

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that highlight distinctions between various entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ueller
    -0.71
    ossession
    -0.69
    ``
    -0.69
    earance
    -0.68
    oke
    -0.65
    ony
    -0.64
    aping
    -0.62
    went
    -0.62
    anqu
    -0.62
    onding
    -0.61
    POSITIVE LOGITS
    worldly
    0.99
     kinds
    0.90
     types
    0.85
     facets
    0.84
     sectors
    0.81
     mammals
    0.80
     countries
    0.78
     implementations
    0.77
     eras
    0.76
     categories
    0.74
    Act Density 0.106%

    No Known Activations