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

    Neuronpedia

    INDEX
    Explanations

    words with the suffix "-al"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PW
    -0.92
     Petersen
    -0.88
     Perkins
    -0.80
     Winn
    -0.77
     whist
    -0.76
     Sands
    -0.76
    ware
    -0.74
    WARE
    -0.74
    isu
    -0.73
     Dos
    -0.72
    POSITIVE LOGITS
    al
    1.63
    AL
    1.49
    alis
    1.35
    als
    1.33
    alist
    1.33
    ally
    1.19
    alian
    1.15
    alm
    1.15
    alore
    1.15
    ALS
    1.14
    Act Density 0.141%

    No Known Activations