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

    Neuronpedia

    INDEX
    Explanations

    the word "of" followed by various other words

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of "ideas."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WF
    -0.74
     ILCS
    -0.72
    keys
    -0.70
    DAQ
    -0.65
    iaries
    -0.65
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
    ï¸ı
    -0.63
    Emb
    -0.63
    CTV
    -0.63
    ECA
    -0.62
    POSITIVE LOGITS
     communism
    0.70
    matically
    0.70
     limitless
    0.69
     donating
    0.68
     marrying
    0.67
     creating
    0.67
    unin
    0.67
    pired
    0.66
     hindsight
    0.66
     quitting
    0.66
    Act Density 0.114%

    No Known Activations