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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating pointed out or highlighted information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating observation or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prus
    -0.68
    estern
    -0.68
    izens
    -0.61
    rig
    -0.61
    jing
    -0.61
    ococ
    -0.61
    rency
    -0.59
    addons
    -0.59
    jug
    -0.59
    rang
    -0.58
    POSITIVE LOGITS
    ,.
    0.91
     (),
    0.86
    ,
    0.83
    ,,
    0.80
    .,
    0.76
     wont
    0.70
    ,-
    0.69
    âĶĢ
    0.68
    terday
    0.67
    (),
    0.66
    Act Density 0.078%

    No Known Activations