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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal curiosity or contemplation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of curiosity and personal introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seiz
    -0.70
     Bung
    -0.63
     squats
    -0.62
     +++
    -0.62
     metic
    -0.61
    -+-+
    -0.61
     misunder
    -0.61
     \'
    -0.61
     ensu
    -0.57
     Pros
    -0.57
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.68
    idge
    0.67
     likewise
    0.66
    ern
    0.65
    istani
    0.65
    èĥ
    0.65
    éĥ
    0.64
    nostic
    0.63
    erville
    0.63
    erning
    0.62
    Act Density 1.365%

    No Known Activations