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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or similarity

    oai_token-act-pair · gpt-3.5-turbo

    expressions that refer to collective experiences or generalizations about groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.83
    ornia
    -0.80
    kefeller
    -0.76
    steen
    -0.69
    icut
    -0.65
    ħĭ
    -0.65
    ĸļ
    -0.63
    aeus
    -0.63
    byter
    -0.63
    idel
    -0.62
    POSITIVE LOGITS
     phenomena
    0.71
    catentry
    0.68
     educators
    0.65
     bureaucr
    0.65
     stakeholders
    0.63
     professions
    0.63
     sensible
    0.63
     proverbial
    0.62
    pects
    0.62
     reviewers
    0.62
    Act Density 0.082%

    No Known Activations