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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals associated with political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perture
    -0.80
    perature
    -0.76
    agne
    -0.76
    ulkan
    -0.76
    aturation
    -0.76
    izophren
    -0.71
    apter
    -0.70
    anism
    -0.69
    iflower
    -0.69
    ropolitan
    -0.68
    POSITIVE LOGITS
    bred
    0.82
    issance
    0.76
    weather
    0.75
    yssey
    0.73
    waters
    0.71
    serv
    0.69
    catch
    0.67
    icles
    0.67
    ĪĴ
    0.67
     assemblies
    0.66
    Act Density 0.068%

    No Known Activations