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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "had."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PLS
    -0.67
    resave
    -0.63
    })*/
    -0.63
    StoreMessageInfo
    -0.63
    utnik
    -0.62
     Confucius
    -0.61
    awtextra
    -0.61
     itſelf
    -0.60
    .*/
    -0.60
    bmatrix
    -0.60
    POSITIVE LOGITS
     tuvo
    0.83
    Had
    0.73
     Had
    0.72
     tuvieron
    0.69
     tiveram
    0.69
     tuvimos
    0.68
     gehad
    0.67
    flashdata
    0.67
    tuvo
    0.66
     tuve
    0.65
    Act Density 0.116%

    No Known Activations