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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political uprisings and movements

    oai_token-act-pair · gpt-3.5-turbo

    the word "ris" and related variations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.89
    erm
    -0.77
    ¥ŀ
    -0.70
    eatures
    -0.69
    resso
    -0.68
     EntityItem
    -0.68
    ļé
    -0.67
    erest
    -0.65
    ntil
    -0.65
     lump
    -0.64
    POSITIVE LOGITS
    sey
    0.96
    quez
    0.88
    coe
    0.84
    cano
    0.83
    ques
    0.81
    pan
    0.81
    pect
    0.78
    py
    0.77
    andra
    0.77
    bane
    0.76
    Act Density 0.008%

    No Known Activations