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

    Neuronpedia

    INDEX
    Explanations

    instances where there is a comparison or contrast between two entities

    oai_token-act-pair · gpt-3.5-turbo

    discussions of relationships or comparisons between two entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vich
    -0.87
    enhagen
    -0.82
    xus
    -0.79
    ucked
    -0.79
    anooga
    -0.78
    ertodd
    -0.73
    maxwell
    -0.73
    nown
    -0.72
    itness
    -0.72
    renheit
    -0.71
    POSITIVE LOGITS
     halves
    1.39
     sexes
    1.34
     extremes
    1.26
     sides
    1.19
     genders
    1.15
     worlds
    1.10
     realms
    1.10
     parties
    1.06
     eras
    1.03
     cultures
    0.98
    Act Density 0.126%

    No Known Activations