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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or events

    oai_token-act-pair · gpt-3.5-turbo

    special character tokens or delimiters indicating structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.75
     Azerb
    -0.68
     Niet
    -0.68
     tradem
    -0.64
    stood
    -0.61
    ilaterally
    -0.60
    edIn
    -0.59
    lear
    -0.58
     Chero
    -0.56
    anamo
    -0.56
    POSITIVE LOGITS
     ].
    0.69
     ]
    0.67
    actionDate
    0.65
     Psy
    0.64
     ::
    0.62
    CRIPTION
    0.59
    hift
    0.58
     ];
    0.57
     largeDownload
    0.55
    photos
    0.54
    Act Density 0.191%

    No Known Activations