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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technological elements

    oai_token-act-pair · gpt-3.5-turbo

    words that imply a state of being wrong or incorrect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Western
    -0.64
    RELATED
    -0.60
     Vanderbilt
    -0.59
    TEXTURE
    -0.59
    SEC
    -0.58
    Repeat
    -0.57
     Vaugh
    -0.57
    SPONSORED
    -0.57
    Mobil
    -0.56
    AUD
    -0.56
    POSITIVE LOGITS
     english
    0.93
    ername
    0.86
    jriwal
    0.77
    hai
    0.75
     oun
    0.74
     cs
    0.74
    ugu
    0.72
    =""
    0.72
     adv
    0.71
    É
    0.70
    Act Density 0.319%

    No Known Activations