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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe the prominence or notable characteristics of something

    oai_token-act-pair · gpt-3.5-turbo

    emphasized adjectives or descriptions that denote notable features or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORTS
    -0.85
    renheit
    -0.78
    ruary
    -0.74
    ople
    -0.74
    States
    -0.74
    ceans
    -0.70
    anners
    -0.66
    ULTS
    -0.66
    PATH
    -0.65
    aval
    -0.65
    POSITIVE LOGITS
     aspect
    1.52
     thing
    1.45
     pecul
    1.19
     feature
    1.18
     facet
    1.17
     part
    1.11
     factor
    1.10
     consequence
    1.06
     element
    1.06
     takeaway
    1.05
    Act Density 0.173%

    No Known Activations