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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     topic
    -0.78
     metic
    -0.73
     limb
    -0.72
     mathemat
    -0.72
     dossier
    -0.71
     detail
    -0.70
     territorial
    -0.69
     stake
    -0.68
     vulner
    -0.68
     contested
    -0.68
    POSITIVE LOGITS
    ï¸ı
    1.22
    ï¸
    0.96
    there
    0.95
    RIP
    0.89
    ãĥĥãĥī
    0.87
    âĹ¼
    0.87
    nob
    0.86
    sure
    0.85
    everyone
    0.85
    hey
    0.84
    Act Density 0.030%

    No Known Activations