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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of cities

    oai_token-act-pair · gpt-3.5-turbo

    lists of places or groups in a comparative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uria
    -0.76
    culosis
    -0.65
    iquette
    -0.65
    rina
    -0.65
    ograph
    -0.65
    ienne
    -0.64
    ="/
    -0.63
    =#
    -0.63
    uristic
    -0.62
    ixir
    -0.61
    POSITIVE LOGITS
     respectively
    2.18
    depending
    1.10
     alike
    1.02
    both
    0.96
     together
    0.90
     depending
    0.85
    together
    0.85
     respective
    0.84
     jointly
    0.84
     totaling
    0.83
    Act Density 0.282%

    No Known Activations