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

    Neuronpedia

    INDEX
    Explanations

    organizations and locations based on the naming conventions used

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and specific individuals involved in political or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atively
    -0.80
    iosity
    -0.78
    acies
    -0.75
    ties
    -0.74
    cair
    -0.73
    itar
    -0.73
    ipeg
    -0.71
    itates
    -0.71
    iar
    -0.71
    itan
    -0.71
    POSITIVE LOGITS
    ĸļ
    0.81
    Mobil
    0.68
    oulos
    0.68
    ħĭ
    0.66
    conservancy
    0.65
    ĨĴ
    0.65
    leon
    0.64
    hammad
    0.64
    velop
    0.63
     Wyatt
    0.60
    Act Density 0.114%

    No Known Activations