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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    specific types of word endings or morphological patterns, particularly those involving suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Waters
    -0.79
     Strait
    -0.75
     Marketplace
    -0.74
     Dull
    -0.74
     Darling
    -0.73
    Bright
    -0.70
     Wast
    -0.70
     Commons
    -0.70
     Subtle
    -0.69
     Bridge
    -0.68
    POSITIVE LOGITS
    agra
    0.91
    ule
    0.78
    atri
    0.77
    ophobic
    0.76
    olith
    0.73
    geoning
    0.73
    Åį
    0.72
    Äĵ
    0.72
    otomy
    0.71
    keyes
    0.70
    Act Density 0.233%

    No Known Activations