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

    Neuronpedia

    INDEX
    Explanations

    law-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "Ļ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.85
     disadvant
    -0.82
    anium
    -0.74
     imitation
    -0.73
     carbohyd
    -0.69
    ierrez
    -0.68
    aneers
    -0.64
     dossier
    -0.63
     vulner
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.22
    VERTISEMENT
    0.86
    sure
    0.86
    Balt
    0.84
    女
    0.80
    ··
    0.78
    ï¸
    0.76
    ution
    0.74
    ship
    0.73
    Spoiler
    0.72
    Act Density 0.344%

    No Known Activations