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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or contrast between two entities

    oai_token-act-pair · gpt-3.5-turbo

    references to contrasting pairs or comparisons between two entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.84
    terday
    -0.79
    levard
    -0.79
    utor
    -0.78
    iggurat
    -0.74
    itant
    -0.73
    xus
    -0.72
    ursday
    -0.72
    itness
    -0.71
    xp
    -0.70
    POSITIVE LOGITS
     halves
    1.36
     extremes
    1.32
     sexes
    1.27
     worlds
    1.27
     universes
    1.20
     sides
    1.10
     genres
    1.10
     genders
    1.09
     parties
    1.08
     styles
    1.07
    Act Density 0.114%

    No Known Activations