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

    Neuronpedia

    INDEX
    Explanations

    phrases related to national and government issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bane
    -0.89
    wright
    -0.85
    enger
    -0.84
    ying
    -0.83
    holes
    -0.82
    lda
    -0.79
    YE
    -0.78
    eva
    -0.77
    bender
    -0.76
    qt
    -0.73
    POSITIVE LOGITS
    ized
    1.24
    ities
    1.20
    ization
    1.17
    ised
    1.16
    ITY
    1.12
    ity
    1.05
    isation
    1.00
    ism
    0.98
    izing
    0.98
    ité
    0.97
    Act Density 2.608%

    No Known Activations