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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal development and learning

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating assistance or support in decision-making or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Border
    -0.77
    QB
    -0.70
    ãĥĩ
    -0.70
    ãĥĺ
    -0.68
    Aust
    -0.67
     Nirvana
    -0.66
    ashed
    -0.66
    æ°
    -0.65
    Reward
    -0.65
    Road
    -0.64
    POSITIVE LOGITS
     nonetheless
    1.51
     nevertheless
    1.45
     certainly
    1.08
     anecd
    0.87
     definitely
    0.86
     sure
    0.83
     surely
    0.82
     suggestive
    0.81
     indirectly
    0.79
     implied
    0.78
    Act Density 0.461%

    No Known Activations