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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numbers or ordering

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Libre
    -0.77
    obo
    -0.71
    oba
    -0.71
    rained
    -0.70
     Olivia
    -0.69
    arella
    -0.68
    runtime
    -0.66
    ial
    -0.66
    oli
    -0.65
     Rapp
    -0.64
    POSITIVE LOGITS
    inburgh
    0.80
    éĹĺ
    0.79
     reluct
    0.79
    selves
    0.75
    resents
    0.75
    borgh
    0.68
    doms
    0.67
    orthern
    0.67
    gencies
    0.66
    sonian
    0.66
    Act Density 0.021%

    No Known Activations