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

    Neuronpedia

    INDEX
    Explanations

    social media information

    oai_token-act-pair · gpt-3.5-turbo

    numeric or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.76
     Fisheries
    -0.74
    rays
    -0.73
     submar
    -0.65
     Stew
    -0.64
    hement
    -0.63
    ateurs
    -0.58
     stewards
    -0.58
     throwing
    -0.57
     siph
    -0.57
    POSITIVE LOGITS
    EGIN
    0.92
    CHAPTER
    0.91
    Anonymous
    0.86
    robe
    0.83
    ---------
    0.83
    è¦ļéĨĴ
    0.82
    âĪ
    0.82
    icide
    0.81
    Follow
    0.80
    Original
    0.79
    Act Density 0.101%

    No Known Activations