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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conveying a message or gaining understanding

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reminis
    -0.64
    Lago
    -0.63
    ãĥĺ
    -0.59
    puff
    -0.59
    seek
    -0.58
    bro
    -0.58
     aloud
    -0.57
    bec
    -0.57
     unsuccessfully
    -0.57
    gat
    -0.57
    POSITIVE LOGITS
     same
    1.01
     brunt
    1.00
     idea
    1.00
     requisite
    0.99
     gist
    0.98
     slightest
    0.98
     opportunity
    0.96
     utmost
    0.96
     hardest
    0.95
     latest
    0.94
    Act Density 0.101%

    No Known Activations