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

    Neuronpedia

    INDEX
    Explanations

    commonalities or shared traits between different entities

    oai_token-act-pair · gpt-3.5-turbo

    references to shared characteristics or similarities between groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.72
    anish
    -0.71
    ¶ħ
    -0.68
    astic
    -0.68
    gomery
    -0.67
    astics
    -0.65
    igers
    -0.63
    ī
    -0.62
    around
    -0.61
    enth
    -0.61
    POSITIVE LOGITS
     similarities
    0.96
     responsibility
    0.95
     common
    0.91
     characteristics
    0.82
     ancestry
    0.82
     traits
    0.78
    same
    0.77
    alities
    0.76
     responsibilities
    0.76
     sensibilities
    0.76
    Act Density 0.056%

    No Known Activations