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

    Neuronpedia

    INDEX
    Explanations

    terms related to flexibility or bending

    oai_token-act-pair · gpt-3.5-turbo

    references to flexibility or adaptable qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Columb
    -0.81
     Peninsula
    -0.74
     Gore
    -0.73
    FORE
    -0.70
     Hurricanes
    -0.67
    keepers
    -0.66
     Ghana
    -0.64
     Nare
    -0.63
    ñ
    -0.62
     Reincarn
    -0.62
    POSITIVE LOGITS
     flex
    1.27
    ibly
    1.21
    ibilities
    1.21
    ible
    1.16
    ibility
    1.13
    itime
    1.11
    flex
    0.99
    arious
    0.91
    ibles
    0.88
    ibl
    0.87
    Act Density 0.006%

    No Known Activations